CN107078937A - Method for reachability management in computer networks - Google Patents

Method for reachability management in computer networks Download PDF

Info

Publication number
CN107078937A
CN107078937A CN 201580057692 CN201580057692A CN107078937A CN 107078937 A CN107078937 A CN 107078937A CN 201580057692 CN201580057692 CN 201580057692 CN 201580057692 A CN201580057692 A CN 201580057692A CN 107078937 A CN107078937 A CN 107078937A
Authority
CN
Grant status
Application
Patent type
Prior art keywords
network
virtual
partition
cover
lrag
Prior art date
Application number
CN 201580057692
Other languages
Chinese (zh)
Inventor
房路渊
F·奇希
V·吉尔
D·班萨尔
Original Assignee
微软技术许可有限责任公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date

Links

Classifications

    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L45/00Routing or path finding of packets in data switching networks
    • H04L45/02Topology update or discovery
    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00Arrangements for program control, e.g. control units
    • G06F9/06Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/44Arrangements for executing specific programs
    • G06F9/455Emulation; Interpretation; Software simulation, e.g. virtualisation or emulation of application or operating system execution engines
    • G06F9/45533Hypervisors; Virtual machine monitors
    • G06F9/45558Hypervisor-specific management and integration aspects
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L12/00Data switching networks
    • H04L12/28Data switching networks characterised by path configuration, e.g. local area networks [LAN], wide area networks [WAN]
    • H04L12/46Interconnection of networks
    • H04L12/4604LAN interconnection over a backbone network, e.g. Internet, Frame Relay
    • H04L12/462LAN interconnection over a bridge based backbone
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L12/00Data switching networks
    • H04L12/28Data switching networks characterised by path configuration, e.g. local area networks [LAN], wide area networks [WAN]
    • H04L12/46Interconnection of networks
    • H04L12/4633Interconnection of networks using encapsulation techniques, e.g. tunneling
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L12/00Data switching networks
    • H04L12/28Data switching networks characterised by path configuration, e.g. local area networks [LAN], wide area networks [WAN]
    • H04L12/46Interconnection of networks
    • H04L12/4641Virtual LANs, VLANs, e.g. virtual private networks [VPN]
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00Arrangements for maintenance or administration or management of packet switching networks
    • H04L41/12Arrangements for maintenance or administration or management of packet switching networks network topology discovery or management
    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00Arrangements for program control, e.g. control units
    • G06F9/06Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/44Arrangements for executing specific programs
    • G06F9/455Emulation; Interpretation; Software simulation, e.g. virtualisation or emulation of application or operating system execution engines
    • G06F9/45533Hypervisors; Virtual machine monitors
    • G06F9/45558Hypervisor-specific management and integration aspects
    • G06F2009/4557Distribution of virtual machine instances; Migration and load balancing aspects
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L12/00Data switching networks
    • H04L12/28Data switching networks characterised by path configuration, e.g. local area networks [LAN], wide area networks [WAN]
    • H04L12/46Interconnection of networks
    • H04L12/4604LAN interconnection over a backbone network, e.g. Internet, Frame Relay
    • H04L2012/4629LAN interconnection over a backbone network, e.g. Internet, Frame Relay using multilayer switching, e.g. layer 3 switching
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L45/00Routing or path finding of packets in data switching networks
    • H04L45/54Organization of routing tables

Abstract

Various techniques for partitioning an overlay network is disclosed herein. In certain embodiments, an overlay network can be partitioned into overlay partitions with manageable sizes. Each overlay partition can independently manage and update reachability information only for end points that belong to a virtual network with at least one end point in the overlay partition. Thus, each overlay partition can operate independently from others to achieve fast reachability updating for relocated virtual machines or other end points.

Description

用于计算机网络中的可达性管理的方法 The method for computer network reachability management

背景技术 Background technique

[0001] 计算机网络可以具有经由有线或无线网络链路通过路由器、交换机、桥接器或其他网络设备在底层网络中彼此互连的大量物理服务器。 [0001] The computer network may have a number of physical servers via wired or wireless network link routers, switches, bridges, or other network devices interconnected with each other in the underlying network. 每个物理服务器可以托管由底层网络支持的一个或多个虚拟覆盖网络中彼此互连的多个虚拟化服务器或虚拟网络功能。 Each physical server can be hosted by one or more underlying network supported virtual overlay network interconnected with each other the plurality of virtual servers or virtual network function. 虚拟覆盖网络的网络节点和网络端点可以根据一个或多个网络协议经由底层网络交换消息。 Virtual overlay network node and a network endpoint can exchange messages via a network of a network according to one or more of the underlying network protocol.

发明内容 SUMMARY

[0002] 提供本发明内容以便以简化的形式介绍将在以下具体实施方式中进一步描述的一些概念。 [0002] This Summary is provided to introduce a selection of concepts that are further described in the following detailed description of a simplified form. 本发明内容不旨在标识所要求保护的主题的关键特征或必要特征,也不旨在用于限制所要求保护的主题的范围。 The present invention is not intended to identify the subject matter of the key features or essential features, nor is it intended to limit the subject matter claimed.

[0003] 与设计和操作计算机网络相关联的一个困难是可扩展性。 [0003] One difficulty with the design and operation of computer networks is associated scalability. 随着物理和/或虚拟化服务器的数目增加,必要资源的量以及操作复杂性快速增加。 With the increase in the number of physical and / or virtual servers, the amount of necessary resources and the complexity of the rapid increase in operations. 例如,由于电力系统故障、负载平衡和/或其他原因,虚拟机可能从一个物理服务器重新定位到另一物理服务器。 For example, since the power system fault, load balancing and / or other reasons, the virtual machine may be relocated from one physical server to another physical server. 重新定位的虚拟机的新地址被更新到对应虚拟网络中的其他虚拟机。 The new address re-positioning of the virtual machine is updated to the corresponding virtual network of other virtual machines. 然而,随着虚拟机的数目达到数百万或数千万,这种地址更新可能涉及大量信息并且可能花费相当大的时间量,在该时间期间与重新定位的虚拟机的通信可能是不可靠的。 However, as the number of virtual machines in the millions or tens of millions, this update addresses may involve large amounts of information and can take a considerable amount of time, during which time the virtual machine communication relocated and may be unreliable of. 因此,可能发生服务中断或者甚至系统故障。 Therefore, it may happen even service interruptions or system failures.

[0004] 所公开的技术的若干实施例可以通过将覆盖网络分区为具有可管理大小的覆盖分区来提高计算机网络的可扩展性。 [0004] Some embodiments of the disclosed technology can be obtained by the overlay network partition having a partition cover manageable size to improve the scalability of a computer network. 每个覆盖分区可以独立地管理和/或更新仅针对具有覆盖分区中的至少一个端点的虚拟网络的可达性信息。 Each partition can be managed independently covering and / or update only reachability information for virtual network having at least one end of the cover partition. 对于不具有覆盖分区中的任何端点的虚拟网络,覆盖分区不管理与这样的虚拟网络相关的任何可达性信息。 For the endpoint does not have to cover any partition of the virtual network, covering partition does not manage any reachability information related to such virtual network. 因此,每个覆盖分区可以独立于其他覆盖分区操作,以实现虚拟机、虚拟网络功能和/或其他合适端点的快速可达性更新。 Thus, each independently of the other partition cover covering partition operations for fast reachability update the virtual machine, the virtual network functions and / or other suitable endpoint.

附图说明 BRIEF DESCRIPTION

[0005]图1是示出根据所公开的技术的实施例的具有覆盖网络分区的计算机网络的示意图。 [0005] FIG. 1 is a diagram illustrating a computer network having overlay network partition according to embodiments of the disclosed technology.

[0006]图2是示出根据所公开的技术的实施例的适用于图1的计算机网络的示例分层底层网络的示意图。 [0006] FIG. 2 is a diagram showing an example of a hierarchical network in accordance with the bottom of FIG 1 applied to the embodiment of the disclosed computer network technology.

[0007]图3是示出根据所公开的技术的实施例的计算机网络的示例操作的示意图。 [0007] FIG. 3 is a schematic diagram illustrating an exemplary embodiment of the computer network of the disclosed technology operations. 为了清楚起见,省略了图1中的计算机网络的某些部分。 For clarity, the omitted parts of the computer network 1 in FIG.

[0005] 图4是示出根据所公开的技术的附加实施例的计算机网络的示例操作的示意图。 [0005] FIG. 4 is a diagram showing an example of a computer network according to additional embodiments of the disclosed technology operations. 为了清楚起见,省略了图1中的计算机网络的某些部分。 For clarity, the omitted parts of the computer network 1 in FIG.

[0009]图5是示出根据所公开的技术的另外的实施例的计算机网络的示例操作的示意图。 [0009] FIG. 5 is a schematic diagram illustrating an example computer network according to a further embodiment of the disclosed technology operations. 为了清楚起见,省略了图1中的计算机网络的某些部分。 For clarity, the omitted parts of the computer network 1 in FIG.

[0010]图6是示出根据所公开的技术的实施例的本地可达性接入网关的软件部件的框图。 [0010] FIG. 6 is a block diagram of software components in accordance with the local access gateway up the embodiments of the disclosed technology.

[0011] 图7是示出根据所公开的技术的实施例的更新图1的计算机网络中的可达性信息的过程的流程图。 [0011] FIG. 7 is a flowchart showing the process of a computer network reachability information update diagram of an embodiment of the disclosed technique in accordance with an.

[0012] 图8是示出根据所公开的技术的实施例的更新图1的计算机网络中的可达性信息的另一过程的流程图。 [0012] FIG 8 is a flowchart showing the process of a computer network according to another embodiment of the update map technique disclosed in 1 reachability information of.

[0013] 图9是示出根据所公开的技术的实施例的管理覆盖分区中的可达性信息的过程的流程图。 [0013] FIG. 9 is a flowchart illustrating a process of managing an embodiment of the disclosed technology reachability information covering the partition.

[0014] 图10是示出根据所公开的技术的实施例的管理覆盖分区中的可达性信息的另一过程的流程图。 [0014] FIG. 10 is a flowchart illustrating another embodiment of the process management techniques disclosed covered partition the reachability information.

[0015] 图11是示出根据所公开的技术的实施例的重新定位虚拟租户端点的过程的流程图。 [0015] FIG. 11 is a flowchart showing a virtual endpoint tenant repositioning embodiment according to the process disclosed in the art.

[0016] 图12是适用于图1中的计算机网络的某些部件的计算设备。 [0016] FIG. 12 is a computing device suitable for use in some of the components of FIG. 1 in a computer network.

具体实施方式 Detailed ways

[0017] 以下描述用于划分、管理和/或更新覆盖网络的系统、设备、部件、模块、例程和过程的某些实施例。 [0017] The following description is divided, in some embodiments the management and / or update the overlay network system, devices, components, modules, routines and processes. 在下面的描述中,包括部件的具体细节以提供对所公开的技术的某些实施例的透彻理解。 In the following description, including the specific details of the components to provide a thorough understanding of the techniques disclosed in certain embodiments. 相关领域的技术人员还将理解,该技术可以具有附加实施例。 Relevant art will also appreciate that the techniques may have additional embodiments. 在没有下面参考图1-12描述的实施例的几个细节的情况下也可以实现该技术。 In the few details of the embodiments described below with reference to FIGS. 1-12 of the case of this technique can also be achieved.

[0018]如本文中所使用的,术语“计算机网络”通常是指具有多个网络节点的互连网络, 网络节点将多个端点彼此连接以及与其他网络(例如,因特网)连接。 [0018] As used herein, the term "computer network" generally refers to interconnected network, the network node having a plurality of network nodes to a plurality of endpoints connected to each other and with other networks (e.g., Internet) connection. 术语“网络节点”通常是指物理和/或软件仿真(或虚拟)网络设备。 The term "network node" generally refers to a physical and / or emulation software (or virtual) network device. 示例网络节点包括路由器、交换机、集线器、桥接器、负载平衡器、安全网关、防火墙、网络名称转换器或名称服务器。 Examples of network nodes including routers, switches, hubs, bridges, load balancers, security gateways, firewalls, network name or name server converter.

[0019]支持虚拟或物理网络设备、网络节点和网络端点的计算机网络在概念上可以划分为在底层网络上实现的覆盖网络。 [0019] support virtual or physical network device, the network node and the network endpoint in a computer network can be divided conceptually into underlying network implemented on the overlay network. “覆盖网络”通常是指在底层网络之上实现并且操作的抽象网络,底层网络可以包括彼此互连并且与物理端点互连的多个物理网络节点。 "Overlay network" generally refers to the implementation of the abstract operation over the network and the underlying network, the underlying network may comprise a plurality of interconnected with each other and with the physical network nodes interconnected physical endpoints. 例如,覆盖网络可以包括在底层网络上实现的一个或多个虚拟网络。 For example, overlay network may comprise one or more virtual networks on the underlying network. 虚拟网络将多个物理服务器或托管在由底层网络中的物理网络节点互连的不同物理服务器上的虚拟化服务器互连。 The virtual network or a plurality of physical servers hosted by the virtualization server on the physical network interconnecting the underlying network nodes are interconnected in a different physical servers. 覆盖网络中的虚拟网络节点可以通过虚拟或逻辑链路彼此连接,虚拟或逻辑链路分别单独地与沿着底层网络中的一个或多个物理网络节点的一个或多个路径相对于。 Virtual network node in the overlay network may be connected by virtual or logical links to one another, a virtual or logical links individually with respect to one or more paths along one or more physical network nodes of the underlying network.

[0020] “虚拟网络”通常是指覆盖网络中的底层网络的一部分的抽象。 [0020] "virtual network" generally refers to abstract the underlying network covering a part of the network. 虚拟网络可以包括被称为“租户站点”的一个或多个虚拟端点,租户站点被用户或“租户”单独地使用以访问虚拟网络和相关联的计算、存储或其他合适资源。 Virtual networks may be referred to as comprising a "tenant site" or more virtual endpoints, be used alone tenant site to access the virtual network and an associated computing, storage or other suitable resources or users "tenant." 租户站点可以托管一个或多个租户端点(“TEP”),例如虚拟机。 Tenants site can host one or more tenants endpoint ( "TEP"), such as a virtual machine. 租户站点还可以包括虚拟路由表(“VRT”),VRT包含针对在特定虚拟网络中的TEP之间路由消息的可达性信息。 Tenants site may also include virtual routing table ( "VRT"), VRT includes reachability information for routing messages between the TEP for the particular virtual network. 例如,可达性信息可以包括虚拟端点到虚拟端点当前驻留的底层网络中的网络节点的地址的映射。 For example, reachability information may include a virtual endpoint to the virtual address mapping underlying network endpoint currently resides in the network node.

[0021] “网络虚拟化边缘”或“NVE”通常是指将一个或多个租户站点连接到它们相应的虚拟网络的在底层网络的边缘处的网络实体。 [0021] "network virtualization edge" or "NVE" generally refers to a network entity or a plurality of tenants connected to their respective sites at the edge of the virtual network in the underlying network. 在一个示例中,基于多协议标签交换网络(MPLS )的虚拟专用网络(“VPN”)中的网络虚拟化边缘是VPN提供商边缘。 In one example, based on multi-protocol label switching network (MPLS) virtual private network ( "VPN") in the virtual network is a VPN provider edge edge. “虚拟化网络功能”或“VNF”通常是指在覆盖网络中实现并且驻留在服务器或网络节点中的网络功能。 "Virtual network function" or "VNF" refers generally implemented in the overlay network and a server that resides in a network node or network functions. 示例VNF包括软件负载平衡器、虚拟防火墙和虚拟网络名称转换器。 Examples of VNF including software load balancers, virtual firewalls and virtual network names converter.

[0022]术语“端点”通常是指物理或软件仿真的计算设备。 [0022] The term "endpoint" refers generally to a physical computing device or a software simulation. 示例端点包括网络服务器、网络存储设备、个人计算机、移动计算设备(例如,智能电话)、网络功能虚拟化、或虚拟机。 Example endpoints include network servers, network storage devices, a personal computer, a mobile computing device (e.g., smart phone), the network virtualization function, or virtual machine. 每个端点可以与在计算机网络中可以具有不同值的端点标识符相关联。 Each endpoint identifier may be associated with the endpoint may have different values ​​in a computer network. 端点标识符(或网络节点标识符)的示例可以至少包括在MPLS网络中使用的标签的一部分、在MPLS网络中使用的标签的堆栈、根据因特网协议(“IP”)的一个或多个地址、一个或多个虚拟IP地址、虚拟局域网中的一个或多个标签、一个或多个媒体访向控制地址、一个或多个Lambda (拉姆达)标识符、一个或多个连接路径、一个或多个物理接口标识符、或者一个或多个分组报头或封装。 Example endpoint identifier (or network node identifier) ​​may comprise using at least part of the label in the MPLS network, use the label stack in the MPLS network in accordance with an internet protocol ( "IP") or a plurality of addresses, one or more virtual IP addresses, virtual local area network of one or more labels to one or more media access control address, the one or more lambda (lambda) identifier, or a plurality of connection paths, or a a plurality of physical interface identifier, or one or more packet headers or encapsulation.

[0023]术语“±或”通常是指底层网络的物理或逻辑分区。 [0023] The term "or ±" generally refers to a physical or logical partitioning of the underlying network. 域可以包括底层网络中的彼此互连和/或与多个端点互连的选择数目的网络节点。 Domain may include a selected number of network nodes in underlying network interconnected with each other and / or interconnected with a plurality of endpoints. 域还可以连接到一个或多个更高级域,一个或多个更高级域包括将特定域连接到域的层级中的相同或不同级别处的其他域的多个附加网络节点。 Domain may also be connected to one or more domains higher, a higher or more additional network domain comprises a plurality of nodes of the same or other domains at different levels will be connected to a specific domain in the domain hierarchy. 在某些实施例中,软件定义网络(“SDN”)可以用于将底层网络划分为多个域。 In certain embodiments, a software-defined network ( "SDN") may be used for the underlying network is divided into a plurality of domains. 在其他实施例中,底层网络的域中的一个或多个域可以至少部分地是使用分布式路由和/或转发协议的分布式计算机网络。 In other embodiments, one or more domains of the underlying network domains may at least in part, using distributed routing and / or forwarding protocol distributed computer network.

[0024]诸如在大规模数据中心中使用的计算机网络可能难以设计和/或操作。 [0024] Computer networks such as used in large scale data centers may be difficult to design and / or operation. 随着物理和/或虚拟化服务器的数目增加,必要资源量或操作复杂性迅速增加。 As the number of physical and / or virtual servers, required resource amount or complexity of the operation increases rapidly. 例如,当多个虚拟机达到数百万或数千万时,更新开始、重新定位或终止的虚拟机的地址可能涉及大量信息并且可能花费大量时间。 For example, when multiple virtual machines in the millions or tens of millions, update began, repositioning or terminate the address of the virtual machine may involve large amounts of information and can take a lot of time. 在这样的地址更新期间,到重新定位的虚拟机的消息仍然可能被路由到重新定位的虚拟机的先前地址,并且因此可能丢失。 During such address updates, to reposition the news of the virtual machine may still be routed to reposition the virtual machine's previous address, and therefore may be lost. 这种不可靠的通信可能导致服务中断或甚至系统故障。 This may lead to unreliable communication service interruptions or even system failure. 所公开的技术的若干实施例可以通过将覆盖网络分区为覆盖分区来解决上述规模和/或更新缺点中的至少一些。 Some embodiments of the disclosed technology may be solved to cover at least some of the above-described partition size and / or disadvantages by updating the overlay network partition. 因此,可以通过包括每个独立地管理可达性信息的附加覆盖分区来扩大计算机网络。 Thus, the computer network may be expanded by including additional covering each partition is independently managed reachability information. 因此,地址更新可以比常规技术更快地完成或“收敛”,从而降低通信中断的风险。 Therefore, the address update can be completed more quickly than conventional techniques or "convergence", thereby reducing the risk of communications downtime.

[0025]覆盖网络中的可达性信息的管理还可以对支持覆盖网络的底层网络施加额外的需求。 [0025] management covering up information networks may also impose additional requirements on the underlying network supports overlay network. 虚拟网络路由和端状态信息通常使用底层网络的控制平面在每个虚拟网络中的端点之间传播。 Virtual network routing and status information is generally used to control the propagation plane of the underlying network in each virtual network between endpoints. 例如,不是每个物理服务器只有一个网络路由,底层网络的控制平面协议可能必须通告在该物理服务器上托管的所有虚拟网络的所有虚拟网络路由。 For example, each physical server is not only a control plane network routing protocols, the underlying network may have all advertised routes the virtual network hosted on the physical server all virtual networks. 当计算机网络被扩大以支持附接到大量虚拟网络的数百甚至数百万个虚拟机时,要维持和传播的可达性信息的绝对体积构成了主要的挑战。 When computer networks are expanding to support large numbers of virtual network attached to hundreds or even millions of virtual machines to maintain and disseminate the absolute volume reachability information constitutes a major challenge.

[0026]图1是示出根据所公开的技术的实施例的具有覆盖网络分区的计算机网络100的示意图。 [0026] FIG. 1 is a diagram illustrating a computer network 100 in accordance with embodiments of overlay network partition of the disclosed technique. 如图1所示,计算机网络100可以包括底层网络120和在底层网络120之上实现和操作的覆盖网络121。 As shown in FIG. 1, the computer network 100 may include network 120 and the underlying implementation and operation of the underlying network 120 over a network 121 coverage. 在所示实施例中,出于说明的目的,覆盖网络121被示出为包括第一、第二、和第三虚拟网络112a、112b和112c。 In the illustrated embodiment, for purposes of illustration, the overlay network 121 is shown to include a first, second, and third virtual network 112a, 112b and 112c. 在其他实施例中,覆盖网络121可以包括任何其他合适数目的虚拟网络和/或虚拟网络功能(未示出)。 In other embodiments, overlay network 121 may include any other suitable number of virtual networks and / or virtual network function (not shown).

[0027] 如图1所示,底层网络120可以包括互连多个服务器102 (分别示出为第一、第二和第三服务器102a_102c)的多个网络节点111 (为了说明目的示出了三个)。 [0027] As illustrated, the underlying network 1120 may include a plurality of network nodes interconnected plurality of servers 111 (illustrated as, respectively, a first, second, and third server 102a_102c) 102 (shown for illustrative purposes a three a). 服务器102可以单独地包括耦合到存储器106和输入/输出部件108的处理器104。 Server 102 may be separately coupled to memory 106 and include an input / output section 108, the processor 104. 处理器102可以包括微处理器、现场可编程门阵列和/或其他合适的逻辑器件。 The processor 102 may include a microprocessor, field programmable gate arrays, and / or other suitable logic device. 存储器104可以包括非暂态易失性和/或非易失性介质(例如,ROM; RAM、磁盘存储介质;光学存储介质;闪存设备、和/或其他合适的存储介质)和/或被配置为存储从处理器102接收的数据以及用于处理器1〇2的指令(例如, 用于执行下面参考图7-^1讨论的方法的指令)的其他类型的计算机可读存储介质。 Non-transitory memory 104 may include volatile and / or nonvolatile media (e.g., ROM; RAM, magnetic disk storage media; optical storage media; flash memory devices and / or other suitable storage media), and / or configured received from the processor to store data and instructions for processor 102 1〇2 (e.g., instructions for a method ^ 7- discussed below with reference to FIG. 1 for performing) of other types of computer-readable storage medium. 输入/输出部件108可以包括显亦器、触換屏、键盘、鼠标、打印机、和/或被配置为接受来自操作者和/或自动软件控制器(未示出)的输入并且向操作者和/或自动软件控制器(未示出)提供输出的其他合适类型的输入/输出设备。 The input / output section 108 may also include a significant, a touch screen for keyboard, mouse, printer, and / or configured to accept from an operator and / or automatic software controller (not shown) and input to the operator and / software or automatic controller (not shown) other suitable type of output from the input / output devices. 即使底层网络120在图1中被不出为具有平面网络结构,但是在某些实施例中,底层网络120可以被组织成多个分层域,如下面参考图2更详细地描述的。 Even if the underlying network 120 is a network not to have a planar configuration in FIG. 1, in some embodiments, the underlying network 120 may be organized into a plurality of stratified domains, as described below with reference to FIG. 2 is described in more detail. 在另外的实施例中,底层网络120可以以其他合适的方式组织。 In a further embodiment, the underlying network 120 may be organized in other suitable manner.

[0028]服务器1〇2可以单独地在存储器1〇6中包含指令,这些指令在由处理器102执行时引起个体处理器1〇2提供管理程序1〇7和NVE 1〇9。 [0028] The server may be separately 1〇2 instructions contained in a memory 1〇6, the instructions cause the processor 1〇2 individuals and to provide management procedures 1〇7 NVE 1〇9 when executed by the processor 102. 管理程序1〇7可以单独地被配置为生成、 监测、终止、和/或以其他方式管理被组织成租户站点110的一个或多个虚拟机114。 1〇7 hypervisor can be individually configured to generate, monitoring, termination, and / or otherwise manage a tenant site 110 is organized into one or more virtual machines 114. 例如,如图1所示,第一服务器l〇2a可以提供分别管理第一和第二租户站点li〇a和ii〇b的第一管理程序107a。 For example, as shown in FIG. 1, the first server may be provided separately l〇2a first and second tenant management station and ii〇b li〇a first hypervisor 107a. 第二服务器10¾可以提供分别管理第二和第三租户站点ii〇b'和110c的第二管理程序107b。 The second server 10¾ be provided separately manage the second and third sites ii〇b tenants' and 110c of the second hypervisor 107b. 第三服务器l〇2c可以提供分别管理第一和第三租户站点ll〇a'和110c'的管理程序107c。 The third server l〇2c be provided separately manage the first and third tenant sites ll〇a 'and 110c' of management program 107c. 租户站点110每个可以包括一个或多个虚拟机114和/或虚拟网络功能(未示出)。 Each tenant site 110 may include one or more virtual machines 114 and / or virtual network function (not shown). 管理程序107在图1中分别被示出为软件部件。 Management program 107 in FIG. 1 are shown as software components. 然而,在其他实施例中,管理程序1〇7每个可以是固件和/或硬件部件。 However, in other embodiments, it may be a hypervisor 1〇7 each firmware and / or hardware components. NVE 109可以被配置为将一个或多个租户站点110连接到它们相应的虚拟网络122。 NVE 109 may be configured as one or more tenants sites 110 are connected to their respective virtual network 122. 即使NVE 109在图1中被示出为单独的软件部件,但是在另外的实施例中,NVE 109可以与对应管理程序107是一体的或者形成是对应管理程序107的一部分。 Even NVE 109 are shown as separate software components in FIG. 1, but in a further embodiment, NVE 109 corresponding to the hypervisor 107 may be integral or formed corresponding to a part of the management program 107.

[0029]如图1所示,不同的服务器102可以单独地托管租户站点110,租户站点11 〇包括针对特定租户1 〇1 (分别被标识为第一、第二和第三租户101a、101b和101c)的多个虚拟机114。 [0029] As shown, different servers 102 may be separately managed site 110 1 tenant, the tenant station 11 comprises a square 101a, 101b for a particular tenant 〇1 1 (respectively identified as a first, second, and third and tenants a plurality 101c) of the virtual machine 114. 例如,第一服务器l〇2a和第三服务器102c都可以为第一租户101a托管租户站点110a和110a'。 For example, the first server and the third server 102c can l〇2a first tenant that tenant hosted sites 110a and 101a 110a '. 第一服务器102a和第二服务器102b都可以为第二租户101b托管租户站点110b和110b'。 The first server 102a and 102b can be thought a second server hosting the second tenant 101b and 110b tenant site 110b '. 第二服务器102b和第三服务器102c都可以为第三租户101c托管租户站点110c和110c '。 The second server 102b and 102c can be thought third server hosting the third tenant 101c and 110c tenant site 110c '. 每个虚拟机114可以执行对应操作系统、中间件和/或应用。 Each virtual machine 114 may perform the corresponding operating system, middleware, and / or applications.

[0030] 覆盖网络121可以包括跨多个服务器102互连特定租户101的租户站点110的一个或多个虚拟网络122。 [0030] overlay network 121 may include a plurality of servers 102 are interconnected across a particular tenant in a tenant sites 101 110 122 or more virtual networks. 例如,第一虚拟网络122a互连在第一服务器102a处和第三服务器102c 处的第一租户站点1 l〇a和110a '。 E.g., 122a in the first virtual network interconnecting the first station 1 l〇a tenant at the first server and the third server 102a and 102c at 110a '. 第二虚拟网络122b互连在第一服务器102a处和第二服务器102b处的第二租户站点110b和110b'。 The second virtual network 122b interconnected second tenant at the site 102a and 110b of the first server at a second server 102b and 110b '. 第三虚拟网络122c互连在第二服务器102b处和第三服务器102c处的第三租户站点110c和110c'。 The third virtual network interconnection 122c in the third tenant at the site 102b and 110c of the second servers at the third server 102c and 110c '. 即使一个虚拟网络122被示出为对应于一个租户101,但是在其他实施例中,多个虚拟网络122可以被分配为对应于单个租户101。 Even if a virtual network 122 is shown to correspond to a tenant 101, in other embodiments, the plurality of virtual network 122 may be assigned 101 to correspond to a single tenant.

[0031] 特定虚拟网络122上的虚拟机114可以经由虚拟网络122彼此通信,即使虚拟机114 被托管在不同的服务器102上。 [0031] The virtual machine 122 on a particular virtual network 114 can communicate with each other via virtual network 122, even if the virtual machine 114 is hosted on a different server 102. 例如,第一服务器102a上的第一租户站点ll〇a的虚拟机114 可以至少部分地基于针对第一虚拟网络122a的第一VRT 112a与第三服务器102c上的第一租户站点1 l〇a '的其他虚拟机114通信。 For example, a first virtual machine ll〇a tenant site on a first server 102a 114 based at least in part for a first tenant 1 l〇a sites on a first virtual network VRT 112a and 122a of the first third server 102c other communication unit 114 'virtual. 在另一示例中,第一服务器l〇2a上的第二租户站点ll〇b的虚拟机114可以至少部分地基于针对第二虚拟网络122b的第二VRT 112b与第二服务器102b上的第二租户站点110b'的其他虚拟机114通信。 In another example, a second tenant site ll〇b virtual machine on the first server 114 may l〇2a second at least partially based on the second virtual network for a second VRT 112b 122b and 102b of the second server tenant communication site other virtual machines 114 110b 'of. 每个虚拟网络122的通信可以与其他虚拟网络122隔离。 Each virtual communication network 122 may be isolated from other virtual network 122. 在某些实施例中,可以允许通信通过安全网关或以其他方式以受控方式从一个虚拟网络122跨越到另一虚拟网络。 In certain embodiments, the communication may be allowed by the security gateway, or otherwise in a controlled manner across from one virtual network 122 to another virtual network. VRT 112可以单独地包含租户地址,每个租户地址包括与特定虚拟网络122中的虚拟化端点或网络节点相对应的虚拟网络标识符。 VRT 112 may contain separately tenant address, each address including a tenant virtual endpoints or network node of a particular virtual network 122 corresponding to the virtual network identifier. 因此, 不同的虚拟网络122可以使用一个或多个相同的虚拟网络标识符和/或标识符值。 Therefore, different virtual network 122 may use one or more of the same virtual network identifier and / or identifier value. 因此,租户可以在每个虚拟网络中使用他/她自己的地址空间,其可以与其他租户的地址空间重叠和/或与由数据中心提供商在数据中心内使用的地址空间重叠。 Therefore, tenants can use his / her own address space for each virtual network, which may overlap with other tenants of the address space and / or overlap with the address space used by the data center provider within the data center. 示例虚拟网络标识符可以包括IP地址、MAC地址和/或其他合适的地址。 Example of a virtual network identifier may comprise an IP address, MAC address and / or other suitable address. 在其他实施例中,不同虚拟网络122的通信可以以其他合适的方式隔离。 In other embodiments, different virtual communication network 122 may be isolated in other suitable manner.

[0032]每个虚拟网络I22还可以允许个体租户1〇1经由底层网络12〇和/或其他合适的网络(例如,因特网)访问对应租户站点110。 [0032] I22 each virtual network may also allow the underlying network via individual tenants 1〇1 12〇 and / or other suitable network (e.g., Internet) 110 to access the corresponding site tenants. 例如,第一租户1 〇1 a可以访问分别由第一服务器102a或第三服务器l〇2c托管的第一租户站点ll〇a或110a'处的虚拟机114中的一个。 For example, a first virtual machine 114 can access a tenant 1 〇1 hosted respectively by the first server or the third server 102a l〇2c site ll〇a first tenant or 110a 'at one. 第二租户101b可以访问分别由第一服务器l〇2a或第二服务器l〇2b托管的第二租户站点ll〇b或ll〇b'处的虚拟机114中的一个。 A second tenant 101b may access hosted respectively by the first server or the second server l〇2b l〇2a virtual machine 114 or second tenant site ll〇b ll〇b 'at the. 第三租户l〇lc可以访问分别由第二服务器102b或第三服务器102c托管的第三租户站点ll〇c或ll〇c'处的虚拟机114中的一个。 The third tenant l〇lc access server are hosted by the second server 102b or 102c of the third virtual machine 114 or a third tenant site ll〇c ll〇c 'at one.

[0033]在操作期间,特定租户站点110处的虚拟机114可能需要重新定位并由不同的服务器102托管。 [0033] During operation, the virtual machine 110 of the particular tenant site 114 may need to reposition hosted by different servers 102. 例如,由于第一服务器l〇2a的系统维护或其他合适的原因,第一租户站点110a 处的一个或多个虚拟机114可能需要重新定位到第三服务器i〇2c。 For example, since the first server l〇2a system maintenance or other reasons appropriate, one or more virtual machines 110a at a first tenant station 114 may need to be relocated to the third server i〇2c. 在重新定位期间,重新定位的虚拟机114可以在第一虚拟网络122a中维持它们相应的虚拟网络标识符(例如,IP地址或MAC地址)。 During repositioning repositioning the virtual machine 114 may maintain their respective virtual network identifier (e.g., IP address or MAC address) in the first virtual network 122a. 然而,例如由底层网络地址标识的这些虚拟机114的物理位置需要从第一服务器102a更新到第三服务器102c。 However, for example, a virtual machine identified by the underlying physical network address location 114 needs to update from the first server 102a to the third server 102c. 如上所述,用重新定位的虚拟机114的新的网络地址更新相同虚拟网络122中的其他虚拟机144可能是耗时的,并且可能导致通信和/或系统故障。 As described above, with the repositioning of the virtual machine 114 a new network address update other virtual machines 122 in the same virtual network 144 can be time consuming, and may result in a communication and / or system failure.

[0034]所公开的技术的若干实施例可以通过(1)逻辑对覆盖网络121进行分区和(2)在逐个分区的基础上独立地更新可达性信息来减少更新重新定位的虚拟机114、己启动的新虚拟机、已终止的虚拟机、新配置的虚拟机、或其他虚拟网络功能(未示出)的网络地址所需的时间量。 [0034] Some embodiments of the disclosed technology can be partitioned and (2) are independently updated reachability information on a partition-by-basis update repositioned to reduce virtual network coverage 114 121 (1) logic, It has started the new virtual machine, the virtual machine has been terminated, the amount of time needed for the new configuration of the virtual machine, a virtual network, or other features (not shown) of the network address. 例如,如图1所示,覆盖网络121基于服务器102被分区为覆盖分区125 (分别单独地标识为第一、第二和第三覆盖分区l25a-125c),每个覆盖分区包括分配的本地可达性接入网关(“LRAG”)m。 For example, as shown in FIG. 1, the overlay network-based server 121 so as to cover the partition 102 is a partition 125 (identified individually as a first, second, and third partition cover l25a-125c), each partition comprising a cover allocated locally of access gateway ( "LRAG") m. 例如,第一服务器102a与具有第一LRAG 124a的第一分区125a相关联。 For example, a first server 102a and the first partition 125a having a first LRAG 124a is associated. 第一服务器10 2a与具有弟一_LRAG 124b的第_•分区12f5b相关联。 The first server 10 2a _LRAG 124b with a first partition 12f5b • _ associated with brother. 第二服务器l〇2a与具有第三LRAG 124c的第三分区125c相关联。 The second and third partition server l〇2a LRAG 124c having a third associated 125c.

[0035]即使基于服务器1〇2划分图1所示的覆盖分区1烈,在其他实施例中,覆盖分区125 也可以基于服务器1〇2、虚拟网络122、虚拟机114的子集、租户站点110、前述的组合中的一个或多个的物理位置来划分,或者可以基于其他合适的物理和/或逻辑实体来划分。 [0035] Even if a strong partition cover shown in FIG. 1 is divided 1〇2 server based, in other embodiments, the cover 125 may be based on partitioning server 1〇2, virtual network 122, a subset of virtual machine 114, tenant site 110, in the combination of one or more physical locations to divide, or may be based on other suitable physical and / or logical entity divided. 下面参考图5更详细地讨论划分覆盖网络121的另一不例模式。 5 discussed in more detail below with reference to FIG not cover the other embodiment modes divide network 121.

[0036] LRAG 1¾可以被配置为仅针对在对应覆盖分区125中具有至少一个端点(例如,虚拟机114)的虚拟网络122独立地填充、更新和/或以其他方式操纵租户站点丨丨〇中的VRT 112。 [0036] LRAG 1¾ may be configured only for having at least one endpoint (e.g., the virtual machine 114) of the virtual network 122 are independently filled, update and / or otherwise manipulated in the corresponding cover partition 125 tenant site Shushu billion in the VRT 112. 例如,第一LRAG IMa可以被配置为操纵与分别通过第一和第二虚拟网络1223和122b 互连的第一和第二租户101a和101b相关联的第一和第二VRT 112a和112b。 For example, a first LRAG IMa may be configured and manipulated through the first and second virtual network 1223 interconnects the first and 122b and 101a and first and second tenant second associated VRT 112a 101b and 112b. 第二LRAG 124b 可以被配置为操纵与分别通过第二和第三虚拟网络l22b和lMc互连的第二和第三租户101a和101b相关联的第二和第三VRT 11¾和112c。 The second LRAG 124b may be configured to be manipulated respectively by the second and third VRT 11¾ l22b second and third virtual network and the second and third interconnect lMc tenant 101a and 101b and associated 112c. 第三LRAG lMc可以被配置为操纵与分别通过第一和第三虚拟网络l22a和122c互连的第一和第三租户l〇la和l〇lc相关联的第一和第三VRT 11¾和Ilk。 The third LRAG lMc may be configured to manipulate the first and the third respectively and VRT 11¾ Ilk and the first and third tenant l〇la l〇lc associated with the first and third virtual network and 122c interconnected l22a . 因此,每个LRAG 124被配置为管理和更新针对有限数目的虚拟网络I22的VRT II2。 Thus, each LRAG 124 is configured to manage and update VRT II2 for a limited number of virtual networks I22. 与每个LRAG 124相对应的虚拟网络I22的数目可以被选择为具有可管理的大小。 The number corresponding to each LRAG 124 I22 virtual network may be selected to have a manageable size. 例如,在图1所示的实施例中,每个LRAG 124对应于两个虚拟网络122。 For example, in the embodiment shown in Figure 1, each LRAG 124 122 corresponding to the two virtual networks. 在其他实施例中,每个LRAG 124可以对应于一个、三个、四个、五个、六个或任何其他合适数目的虚拟网络I22。 In other embodiments, each LRAG 124 may correspond to one, three, four, five, six, or any other suitable number of virtual network I22. 在前述实施例中,LRAG 124可以被配置为通过管理程序107、通过服务器102中的单独代理、或通过分布式协议和服务器102中的对应进程的组合来直接操纵VRT 112。 In the foregoing embodiment, LRAG 124 may be configured 107 by the proxy server 102 alone, or by direct manipulation by VRT 112 by management program corresponding to the combination process and the distributed protocol server 102.

[0037] 在某些实施例中,LRAG 1M还可以被配置为与对应管理程序107协作来实例化、修改、终止和/或以其他方式管理对应覆盖分区125中的虚拟机114。 [0037] In certain embodiments, LRAG 1M 107 may also be configured to cooperate with a corresponding hypervisor to instantiate, modifications, termination and / or otherwise manage the corresponding partition cover 125 in virtual machine 114. 例如,第一LRAG 124a可以使第一管理程序l〇7a实例化针对第一租户站点110a、第二租户站点ll〇b或这两者的一个或多个虚拟机114。 For example, a first LRAG 124a may be the first example of hypervisor l〇7a site for a first tenant 110a, a second tenant site ll〇b or both the one or more virtual machines 114. 在另一示例中,第一LRAG 124a还可以使第一管理程序107终止针对第一租户站点110a、针对第二租户站点110b或这两者的一个或多个虚拟机114。 In another example, the first LRAG 124a may terminate the first hypervisor 107 110a, 110b site for a second tenant, or both, one or more virtual machines 114 for a first tenant site. 在其他实施例中, 前述功能可以由对应服务器102的其他合适的软件、固件和/或硬件部件来执行。 In other embodiments, the functions may be performed by other suitable software, firmware and / or hardware components corresponding to the server 102.

[0038]在所示实施例中,LRAG 1M被示出为独立于对应服务器1〇2的软件部件。 [0038] In the illustrated embodiment, LRAG 1M was shown to be independent of the corresponding server software component 1〇2. 在其他实施例中,LRAG 1M还可以包括固件和/或硬件部件。 In other embodiments, LRAG 1M may also include firmware and / or hardware components. 在某些实施例中,LRAG 124可以由计算机网络100的一个或多个附加服务器(未示出)托管。 In certain embodiments, LRAG 124 may be composed of a computer network 100 or more additional server (not shown) Host. 在其他实施例中,至少一个LRAG 124 (例如,第一LRAG IMa)可以由对应服务器1〇2(例如,第一服务器l〇2a)托管。 In other embodiments, at least a LRAG 124 (e.g., a first LRAG IMa) may be formed from the corresponding server 1〇2 (e.g., the first server l〇2a) hosting. 在另外的实施例中,LRAG 124可以由底层网络12〇的网络节点111和/或其他合适的部件中的一个或多个来托管。 In a further embodiment, LRAG 124 may be formed from the underlying network 12〇 network node 111 and / or other suitable components to host one or more. 在另外的实施例中,LRAG 1M可以以合适的布置具有前述实施例和/其他合适的部件的任何组合。 In a further embodiment, LRAG 1M may have any combination of embodiments and / or other suitable components of the foregoing embodiments in a suitable arrangement.

[0039]计算机网络100还可以包括在操作上耦合至IjLRAG 124的覆盖网络资源管理器126。 [0039] The computer network 100 may also include overlay IjLRAG 124 coupled to a network resource manager 126 in operation. 覆盖网络资源管理器126可以被配置为将计算机网络100的物理资源分配给特定虚拟机114、租户站点110、虚拟网络122、上述的组合、或其他合适的实体。 Overlay network resource manager 126 may be configured to physical resources allocated to a particular virtual machine 114 of computer network 100, 110, virtual network 122, combinations thereof, or other suitable entity tenant site. 例如,在一个实施例中, 覆盖网络资源管理器I26可以将第一服务器102a的资源分配给与第一租户站点ll〇a相关联的一个或多个虚拟机114。 For example, in one embodiment, the overlay network resource manager I26 resource allocation may give a first server 102a is a first tenant ll〇a site associated with one or more virtual machines 114. 在另一示例中,覆盖网络资源管理器126可以将第二服务器102a 的资源分配给相同的一个或多个虚拟机114。 In another example, the overlay network resource manager 126 may allocate resources to the second server 102a the same one or more virtual machines 114.

[0040] 覆盖网络资源管理器126还可以被配置为与和某些覆盖分区125相关联的LRAG 124通信可达性信息。 [0040] overlay network resource manager 126 may also be configured to communicate reachability information LRAG 124 and 125 associated with the certain partitions cover. 示例可达性信息可以包括例如标识其上托管虚拟机114'的物理服务器(例如,第一服务器102a)和/或底层网络120的网络设备111的底层位置标识符或底层网络地址。 Exemplary reachability information may include, for example, identifying which virtual machines hosted 114 'physical server (e.g., a first server 102a) network devices and / or underlying network location identifier 120 underlying or bottom layer 111 of the network address. 底层位置标识符或底层网络地址可以包括以下中的至少一个(或其组合):MPLS标签或MPLS标签的一部分、有序MPLS标签的堆栈、一个或多个IPv4地址、一个或多个IPv6地址、一个或多个虚拟IP地址、一个或多个VLAN标签、一个或多个MAC地址、一个或多个Lambda 标识符、通向端点的一个或多个连接路径、一个或多个物理接口标识符、一个或多个位集合、一个或多个分组报头或封装、或其他合适的位置标识符。 Underlying bottom position identifier or network address may comprise at least one of the following (or combinations thereof): MPLS label or part of MPLS labels, MPLS label stack order, one or more IPv4 addresses, IPv6 addresses one or more, one or more virtual IP addresses, one or more VLAN tags, one or more MAC addresses, one or more identifiers Lambda, or a plurality of connection paths to the endpoint, one or more physical interface identifiers, one or more sets of bits, one or more packet headers or encapsulation, or other suitable location identifiers.

[0041] 可达性信息还可以包括第一虚拟网络122a上的虚拟机114'的虚拟网络标识符、通过底层网络120到达虚拟机114'的路由、和/或其他合适的传输信息。 [0041] The reachability information may further include a virtual machine on a first virtual network 114 122a 'virtual network identifier, the network via 120 reaches the underlying virtual machine 114' routes, and / or other suitable transmission information. 在某些实施例中,传输信息可以包括服务质量信息,诸如如何在底层网络120的网络设备111处对分组进行处理或排队。 In certain embodiments, the transmission information may include a quality of service information, such as how to process the packet queue 111 or network device 120 of the underlying network. 在其他实施例中,传输信息可以包括关于分组是否要经历深度分组检查、经历与服务链相关联的网络功能(例如,防火墙、负载平衡器等)的信息。 In other embodiments, the transmission may include information regarding whether a packet to be subjected to deep packet inspection, service chain experiences associated with network functions (e.g., firewalls, load balancers, etc.) information. 基于可达性信息,LRAG 124可以以及时的方式填充和/或更新对应VRT 112中的条目,并且因此降低通信中断和/或系统故障的风险。 Based on accessibility information, LRAG 124 can be filled in a timely manner and / or update the corresponding entry in the VRT 112, and thus reduce the risk of interruption of communication, and / or system failure. 以下参考图3-5更详细地描述覆盖网络资源管理器126和LRAG 124的操作的若干示例。 The following example of the operation of several 3-5 overlay network resource manager 126 and LRAG 124 is described in more detail. 在其他实施例中,LRAG 124可以仅使用在覆盖网络121中使用的地址、路由和标识符来填充和/或更新对应VRT 112中的条目。 In other embodiments, LRAG 124 may be filled and / or update the corresponding entry in the VRT 112 only uses the address, routing and network identifier used in the cover 121. 这样的地址、路由和标识符到在底层网络120中使用以标识目的地虚拟机114驻留的物理主机的地址和标识符的映射可以由驻留在服务器102中或与服务器102分离的单独的软件、固件和/或硬件实体来执行。 Such an address, using the mapping identifier to the routing and destination virtual machine 114 to identify the physical address and the host identifier reside in the underlying network 120 can be individually separated by residing in the server 102 or server 102 software, firmware and / or hardware entity. 在某些实施例中, LRAG 124可以使用映射信息来配置这样的单独的实体。 In certain embodiments, LRAG 124 may be used to configure this mapping information a separate entity. 在其他实施例中,这样的单独的实体可以由不同的管理实体(未示出)来配置。 In other embodiments, such a separate entity (not shown) managed by a different entity configuration.

[0042]图2是示出根据所公开的技术的实施例的适用于图1的计算机网络100的示例分层底层网络120的示意图。 [0042] FIG. 2 is a diagram showing an example of a hierarchical network in accordance with the bottom of FIG 1 applied to the embodiment of the disclosed technique 120 of computer network 100. 即使在图2中示出了底层网络120的特定布置,但是对覆盖网络121 (图1)进行分区的各种技术可以应用于具有与图2所示的不同的网络节点和/或端点的布置的其他底层网络。 Even in FIG. 2 shows a specific arrangement of the underlying network 120, but various techniques overlay network 121 (FIG. 1) may be applied to a partition arranged in different network nodes shown in Figure 2 and / or endpoints other underlying network. 通常,底层网络120的分区可以独立于覆盖网络121被分区和/或如何分配LRAG 124的方式。 Typically, the partition 120 may be independent of the underlying network in the overlay network 121 and / or the way how to allocate LRAG 124 partitions. 如图2所示,底层网络120可以包括具有一个或多个网络节点111的核心域131。 As shown in FIG. 2, the bottom layer 120 may include a core network domain 131 has one or more network nodes 111. 底层网络120还可以包括一个或多个一级域133。 Underlying network 120 may also include one or more domains 133 a. 图2中出于说明目的示出了两个一级域I33,并且两个一级域133被单独地标识为域D1-1和D1-2。 FIG 2 shows for illustrative purposes a two domains I33, and a two domains 133 are separately identified as a domain D1-1 and D1-2. 在所示实施例中,一级域D1-1包括两个二级域I35 (单独地标识为D2_l和D2-2)。 In the illustrated embodiment, a two second domains comprises domain D1-1 I35 (individually identified as D2_l and D2-2). 一级域D1-2包括一个二级域D2-3。 A domain comprising a second-level domain D1-2 D2-3. 在其他实施例中,一级域104可以包括其他合适数目的域和/或端点。 In other embodiments, a domain 104 may include other suitable number of domains and / or endpoints.

[0043] 二级域106可以单独地包括一个或多个端点141,例如服务器102、一个或多个边缘节点I37、以及将端点108连接到边缘节点137的一个或多个网络节点111。 [0043] The two domains 106 may individually comprise one or more endpoints 141, such as server 102, one or more edge nodes I37, and the endpoint 108 is connected to an edge node 137 or more network nodes 111. 在一个实施例中, 网络节点111可以单独地包括机架顶(“TOR”)路由器或交换机。 In one embodiment, network node 111 may independently comprise a top rack ( "TOR") router or a switch. 在其他实施例中,网络节点111可以包括桥接器、网关或其他合适的通彳目设备。 In other embodiments, the network node 111 may include a bridge, a gateway, or other suitable device through mesh left foot. 在所不实施例中,每个二级域135包括形成边缘节点组的两个边缘节点137(例如,边缘节点EN2-1和EN2-1')。 In embodiments that are not, each region 135 includes two edge nodes forming two edge nodes of the group 137 (e.g., edge node EN2-1 and EN2-1 '). 在某些实施例中,可以随机地访问边缘节点组中的边缘节点137,例如,针对非流量工程类型的分组。 In certain embodiments, the edge node may randomly access edge node group 137, e.g., for non-packet traffic engineering type. 在其他实施例中,可以特别地标识和指定边缘节点组中的边缘节点137中的一个,以处理例如流量工程类型的分组。 In other embodiments, and may be specifically identified edge node designated group of one edge node 137 to handle the type of packet traffic engineering, for example. 在另外的实施例中,可以基于任何其他合适的标准以其他合适的方式来访问边缘节点137。 In a further embodiment, it may be based on any other suitable criteria in other suitable ways to access edge node 137.

[0044]图2所示的分层划分可以以各种方式应用于一个或多个数据中心。 Hierarchical division shown in [0044] FIG. 2 may be applied to one or more data centers in various manners. 例如,在某些实施例中,图2所示的分层划分可以应用于具有核心域131的一个数据中心,核心域丨31包括数据中心的一个或多个T3宽带交换机。 For example, in some embodiments, the hierarchical division shown in FIG. 2 may be applied to a core region 131 of a data center, comprising a core domain Shu data center 31 or more broadband switch T3. 一级域133可以包括连接到具有T1和/或TOR开关的二级域135的T2开关。 A domain 133 may include a connection to a second-level domain having a T1 and / or T2 of TOR switch the switch 135. 在其他实施例中,一级域133可以包括T2和H开关,而二级域135包括TOR 开关。 In other embodiments, the domain 133 may include an H switch and T2, and two 135 comprises a TOR switch domain. 在另一示例中,图2中所示的分层划分也可以应用于多个数据中心。 In another example, a hierarchical division shown in FIG. 2 may also be applied to multiple data centers. 例如,核心域131 可以包括互连多个数据中心和T3宽带交换机的核心网络。 For example, the core may comprise a core network domain 131 interconnecting a plurality of data centers and T3 broadband switches. 在每个数据中心内,一级域133可以包括T2交换机,而二级域可以包括T1和/或TOR交换机。 Within each data center 133 may include a domain switch T2, and T1 may include a second-level domain and / or TOR switch. 在另外的示例中,底层网络120的划分可以包括附加的和/或不同的域级。 In a further example, the partitioning of the underlying network 120 may include additional and / or different domain level.

[0045]在任何前述实施例中,边缘节点U7可以被配置为沿着一个或多个网络路径或隧道143路由去往/来自较高级或较低级域的通信。 [0045] In any of the foregoing embodiments, the edge node may be configured to go U7 along one or more network paths or tunnels 143 routes to / from the higher or lower level communications domain. 例如,从二级域D2-i中的服务器102 '到二级域D2-3中的服务器102”的消息可以经由从网络节点111 '开始到边缘节点£^2-1或EN2-1 ' 并且然后到一级域D1-1的隧道143来路由。一级域D1-1的边缘节点EN1-1可以经由核心域131的网络节点111中的一个或多个将消息转发到一级域D1-2。一级域D1-2然后可以经由边缘节点EN1-2将消息转发到二级域D2_3的边缘节点EN2-3或EN2-3,,其继而经由网络节点111 '将消息转发到服务器102”。 For example, the domain D2-i from the two servers 102 'to the second-level domain server 102 D2-3 "message from the network node via 111' to the start edge node £ ^ 2-1 or EN2-1 'and then to a domain 143 D1-1 tunnel route. D1-1 an edge node domain to a domain can EN1-1 domain network node 111 via the core 131 is one or more of the message forwarding D1- 2. a domain D1-2 message may then be forwarded via the edge node to the second-level domain D2_3 EN1-2 edge node EN2-3 EN2-3 ,, or a network node 111 which in turn 'forwards the message to the server 102 via " . 在某些实施例中,隧道143可以例如利用基于根据例如MPLS 协议的底层网络12〇中的源地址或目的地地址中的至少一个预先计算的网络路由来预先建立。 In certain embodiments, the tunnel 143 may use, for example, based on pre-established according to at least one pre-computed routing network, for example, MPLS 12〇 underlying network protocol source address or destination address. 在其他实施例中,隧道143可以在自组织(ad hoc)的基础上或以其他合适的方式来计算、建立和/或以其他方式形成。 In other embodiments, the tunnel 143 may be calculated or otherwise suitable manner on the basis of the ad-hoc (ad hoc) to establish and / or otherwise formed.

[0046]图3是示出根据所公开的技术的实施例的计算机网络100的示例操作的示意图。 [0046] FIG. 3 is a schematic diagram illustrating an exemplary embodiment of the computer network embodiments disclosed technique 100 operation. 为了清楚起见,图3中省略了计算机网络100的某些部件。 For clarity, FIG. 3 omits some components of the computer network 100. 如图3所示,覆盖网络资源管理器126 可以被配置为向LRAG 124传送关于任何资源分配的信息,例如,向虚拟机114的资源分配、 任何虚拟机11 4和/或虚拟网络功能的重新定位、或其他合适的资源分配操作。 3, the overlay network resource manager 126 may be configured to transmit information about any of the allocated resources LRAG 124, e.g., the resource allocation to the virtual machine 114, virtual machine 114 re any and / or virtual network functions positioning, or other suitable resource allocation operations. 基于这样的信息,个体LRAG 1料然后可以仅针对在对应覆盖分区125中具有至少一个端点的虚拟网络122来配置、更新和/或以其他方式操纵对应虚拟网络122中的虚拟机114、虚拟网络功能和/ 或VRT 112。 Based on such information, the individual LRAG 1 material may then be disposed only for the virtual network 122 having at least one end of the corresponding cover the partition 125, update and / or otherwise manipulating the corresponding virtual network 122, virtual machine 114, virtual network function and / or VRT 112.

[0047]为了用示例进行说明,覆盖网络资源管理器126可以被配置为通知第一LRAG 124a 实例化新虚拟机114'并且将实例化的虚拟机114'附接到第一虚拟网络122a。 [0047] To illustrate with an example, the overlay network resource manager 126 may be configured to notify the first LRAG 124a instantiating a new virtual machine 114 'and the instantiated virtual machine 114' attached to the first virtual network 122a. 在一个实施例中,覆盖网络资源管理器126通过传输可达性信息132来通知第一LRAG 124a。 In one embodiment, the overlay network resource manager 126 is notified by transmitting a first LRAG 124a reachability information 132. 在其他实施例中,覆盖网络资源管理器12e还可以经由应用编程接口和/或其他合适的接口来通知第一LRAG IMa。 In other embodiments, the overlay network resource manager may inform the first 12e further LRAG IMa via an application programming interface and / or other suitable interface. 响应于可达性信息132,第一LRAG l24a(具有图1中的第一管理程序l〇7a)可以实例化所请求的虚拟机114 '并且将虚拟机114 '附接到第一虚拟网络122a。 In response to the reachability information 132, a first LRAG l24a (FIG. 1 having a first hypervisor l〇7a) instantiate the requested virtual machine 114 'and the virtual machine 114' attached to the first virtual network 122a . 然后,第一LRAG 124a可以向覆盖网络资源管理器126传输状态通知134,以报告虚拟机114'的实例化完成并且虚拟机114'被附接到第一虚拟网络122a。 Then, the first LRAG 124a can inform the overlay network 134 to the resource manager 126 transmit status report to the virtual machine 114 'is instantiated and the virtual machine to complete 114' is attached to a first virtual network 122a.

[0048]然后,覆盖网络资源管理器126可以确定哪一个或多个覆盖分区125受到所报告的资源分配的影响,并且将关于资源分配的合适的可达性信息传送给受影响的一个或多个覆盖分区125中的一个或多个对应LRAG 124。 [0048] Then, the overlay network resource manager 126 may determine which of the one or more partitions 125 covering the affected the reported resource allocation, and the appropriate reachability information transmitted on the resource assignment to one or more of the affected one or more partitions 125 covers a corresponding LRAG 124. 例如,在上面的示例中,实例化的虚拟机114 '附接到第一虚拟网络122a,并且因此第一和第三覆盖分区125a和125c受到影响,因为它们包含第一虚拟网络122a的至少一个端点。 For example, in the above example, an instance of the virtual machine 114 'attached to the first virtual network 122a, and thus the first and third covers 125a and 125c partition affected because they comprise a first at least one virtual network 122a endpoint. 相反,第二覆盖分区125b不受影响,因为它不包括第一虚拟网络122a的任何端点。 In contrast, the second partition 125b covering the affected because it does not include any first virtual network endpoint 122a. 然后,覆盖网络资源管理器126可以仅向受影响的覆盖分区I25中的那些LRAG 1放(例如,第一和第三LRAG IMa和124c)传输关于所实例化的虚拟机114'的可达性信息U2,而不向非受影响的一个或多个覆盖分区中的LRAG 124 (例如,第二LRAG 124b)传输相同的信息。 Then, the overlay network resource manager 126 may only be put (e.g., the first and third LRAG IMa and 124c) about the transmission of the virtual machine instance 114 to those affected LRAG I25 partition cover 1 'reachability information U2, without overwriting the same transmission information partition LRAG 124 (e.g., a second LRAG 124b) to a non-affected or more.

[0049]基于所传输的可达性信息,第一和第三LRAG 124a和124c然后可以更新第一和第三VRT 112a和112b以具有针对所实例化的虚拟机114 '的新的或更新后的条目。 [0049] Based on the transmitted reachability information, the first and third LRAG 124a and 124c may then update the first and third VRT 112a and 112b to have a virtual machine instantiated for 114 'new or updated entry. 例如,第一VRT 112a中的条目可以包括针对第一虚拟网络122a上的所实例化的虚拟机114 '的租户地址(例如,虚拟网络地址),因为虚拟机114'是本地的。 For example, the first entry in the VRT 112a may comprise for 114 'tenant address (e.g., a virtual network address), because the virtual machine 114' of the virtual machine instantiated on a first virtual network 122a is local. 第三VRT 112c中的对应条目可以包括针对虚拟机114 '的租户地址和标识例如第一服务器l〇2a的相关联的底层位置标识符。 The corresponding entry in the third VRT 112c may include a bottom location identifier associated with the first virtual machine for server l〇2a 114 'tenant identification and address, for example.

[0050]覆盖网络资源管理器126和LRAG 124还可以协作以将一个或多个虚拟机114从一个服务器102无缝地重新定位到另一服务器。 [0050] overlay network resource manager 126 and LRAG 124 may also cooperate to one or more virtual machines from one server 114 relocated to another server 102 seamlessly. 例如,可以决定将托管在第一服务器1〇2a (以下称为原始虚拟机114')上的虚拟机114'从第一服务器l〇2a重新定位到第三服务器102c。 For example, it is possible to decide the first server is hosted 1〇2a (hereinafter referred to as the original virtual machine 114 ') on the virtual machine 114' relocated from the first server to the third server l〇2a 102c. 这种重新定位的原因可以包括负载平衡、系统升级和/或维护、用户请求、服务器故障、和/ 或其他合适的原因。 The reason for this repositioning may include a load balancing, system upgrades and / or maintenance, a user request, server failure, and / or other appropriate reasons.

[0051]作为初始操作,覆盖网络资源管理器126通过将可达性信息132传输给第三LRAG 124c来在第三服务器l〇2c处准备目标虚拟机114”。基于可达性信息,第三LRAG 124c配置第—虚拟网络122a的NVE 109c (图1)中的VRT 112c。第三LRAG 124c然后与第三管理程序l〇7c (图1)通信以建立和启动目标虚拟机114”。 [0051] As an initial operation, the overlay network 126 via the resource manager 132 reachability information transmitted to the third LRAG 124c in the third server l〇2c to prepare the target virtual machine 114. "Reachability information based on the third LRAG 124c Allocation - virtual network 122a of NVE 109c VRT 112c (FIG. 1) and a third LRAG 124c and the third communication l〇7c hypervisor (FIG. 1) to establish and start the target virtual machine 114. ". 如果第三NVE 109c不包括针对第一虚拟网络122a的任何端点,则可以创建针对目标虚拟机114”的新租户站点110和VRT 112。然后,可以用基于由第三LRAG lMc从覆盖网络资源管理器126接收的信息的信息(例如,地址和/或网络路由)填充VRT II2。如果第三NVE 10%已经包括第一虚拟网络l22a的至少一个端点,则第一租户站点110a'中的目标虚拟机114”可以附接到第一虚拟网络122a。 If the third NVE 109c does not include for any endpoint 122a of the first virtual network, you can create the target virtual machine 114, "the new tenants sites 110 and VRT 112. Then, you can use based on the third LRAG lMc from the overlay network resource management information (e.g., address and / or network routing) 126 receives information filled VRT II2. If the third NVE 10% have a first virtual network comprising at least one endpoint l22a, the target site of the first tenant 110a 'virtual 114 "may be attached to a first virtual network 122a.

[OO52]然后,第三LRAG lMc可以向覆盖网络资源管理器126传输状态通知134,并且向它通知目标虚拟机114”的准备完成。作为响应,覆盖网络资源管理器126通知第一LRAG 124a 开始将原始虚拟机114 '迀移到被托管在第三服务器l〇2c上的目标虚拟机114”。 [OO52] Then, the third LRAG lMc 134 can notify the transmit state 126 overlay network resource manager, and notify it to prepare the target virtual machine 114 "is completed. In response, the overlay network resource manager 126 notifies the first start LRAG 124a the original virtual machine 114 'is moved Gan hosted on a third server 114 l〇2c target virtual machine. " 在某些实施例中,虚拟机114 '的重新定位可以包括从原始虚拟机114 '向目标虚拟机114”传输配置、数据和/或其他合适的信息。 In certain embodiments, the virtual machine 114 'may include repositioning the original virtual machine 114' to the target virtual machine 114 "transmission configuration, data, and / or other suitable information.

[0053]原始虚拟机114 '的重新定位可以根据本文中被称为热、暖或冷重新定位的三种情况。 [0053] Original VM 114 'repositioning three cases may be referred to herein as hot, warm or cold repositioned. 在热重新定位中,原始虚拟机114'从一个服务器102被重新定位到另一服务器,同时继续运行而不在新位置被关闭和重新启动。 Repositioning the heat, the original virtual machine 114 'from a server 102 to be relocated to another server, while continuing to run without being shut down and restarted at the new position. 在暖重新定位中,在存储器或磁盘文件中保存的相关联的配置的情况下暂停原始虚拟机114',并且稍后一旦重新定位完成则重新启动虚拟机114。 Repositioning the warm, pause case of the configuration saved in a memory or a disk file associated original virtual machine 114 'and, once completed later repositioned restarting the virtual machine 114. 在冷重新定位中,原始虚拟机114'被关闭,其中相关联的配置被移动到新主机中的管理程序107,然后虚拟机114 '在新位置被重新启动。 Repositioning the cold, the original virtual machine 114 'is closed, is arranged which is associated to the new host hypervisor 107 and virtual machines 114' is restarted at the new location.

[0054] 在这种重新定位期间,原始虚拟机114 '可以维持其网络状态和连接性信息,例如其租户地址(例如,第一虚拟网络122a中的IP地址)和/或其MAC地址,以防止或至少降低现有TCP会话中断和需要重新启动的风险。 During [0054] In this repositioning, the original virtual machine 114 'may maintain its connectivity and network status information, such as its tenant address (e.g., IP addresses in the first virtual network 122a) and / or MAC address, to prevent or at least reduce the risk of an existing TCP session is interrupted and need to be restarted. 然而,在原始虚拟机114'被重新定位到第三服务器102c时,底层网络120 (图1)中的新主机(即,第三服务器l〇2c)的IP地址必然改变。 However, the original virtual machine 114 'is repositioned to the third server 102c, new underlying host network 120 (FIG. 1) (i.e., the third server l〇2c) bound to the IP address changes.

[0055] 为了在第一虚拟网络12¾中维持原始虚拟机114 '的IP地址,在覆盖网络121中的虚拟机114 '的地址与在底层网络120中的相同虚拟机114的地址解耦。 [0055] In order to maintain the original virtual machine in a first virtual network 114 12¾ 'IP address, the virtual machine 121 in the overlay network 114' is the same as the address in the virtual machine 120 of the underlying network 114 is decoupled address. 例如,在某些实施例中,原始虚拟机114'可以由包括租户虚拟网络标识符(“TVNI”)、租户地址(“TN”)和底层网络地址(“UNA”)的端点标识符标识为TVNI/TA—UNAJVNI标识虚拟机114'附接到的虚拟网络(例如,第一虚拟网络122a)。 For example, in some embodiments, the original virtual machine 114 'may be identified by the endpoint identifier comprises a virtual tenant network identifier ( "TVNI"), Tenant address ( "TN") and the underlying network address ( "UNA") of TVNI / TA-UNAJVNI identify the virtual machine 114 'is attached to the virtual network (e.g., a first virtual network 122a). 租户地址可以包括例如标识第一虚拟网络122a上的虚拟机114 '的IP地址。 Tenant address may include, for example, the IP address of the virtual machine on a first virtual network identifier 122a 114 'of. 底层网络地址标识虚拟机114 '被托管在其上的底层网络120 (图1)中的网络节点。 Underlying network address to identify the virtual machine 114 'are hosted at the network node on which underlying network 120 (FIG. 1). 在其他实施例中,虚拟机114 '可以以其他合适的方式来标识。 In other embodiments, the virtual machine 114 'may be identified in other suitable manner.

[0056]响应于重新定位,可以维持虚拟机114 '的端点标识符的一部分,并且可以调节另一部分。 A portion of the endpoint identifier [0056] In response to repositioning, to maintain the virtual machine 114 ', and another portion may be adjusted. 例如,在一个实施例中,可以维持虚拟机114'的TVNI/TA,使得虚拟机114'在第一虚拟网络122a上具有相同的地址。 For example, in one embodiment, the virtual machine 114 may be maintained apos TVNI / TA, so that the virtual machine 114 'having the same virtual address on the first network 122a. 然而,可以调整UNA以对应于托管目标虚拟机114”的第三服务器1 〇2c。因此,虚拟机114 '的端点标识符可以从TVNI /TA—UNA调节为TVNI /TA^UNA ',其中UNA和UNA'分别对应于第一和第三服务器102a和102c的地址。 However, UNA may be adjusted to correspond to the target virtual machine hosted 114 "1 〇2c third server. Thus, the virtual machine 114 'may be adjusted to endpoint identifier TVNI / TA ^ UNA from TVNI / TA-UNA', wherein UNA and UNA 'respectively corresponding to the first server 102a and 102c and the third address.

[0057]继续上面的示例,响应于来自第三LRAG 124c的状态通知1M,覆盖网络资源管理器126可以向受到虚拟机114 '的重新定位影响的覆盖分区125中的LRAG传输更新后的可达性信息。 [0057] Continuing the example above, in response to a notification from the third state to a 1M LRAG 124c covering network resource manager 126 may provide up to the partition 125 by the transmission coverage LRAG repositioning affecting the virtual machine 114 'in the update information. 与不包含受影响的虚拟网络122的覆盖分区125相关联的LRAG 124不接收任何更新后的可达性信息。 And does not contain the affected virtual network overlay partitions 122 125 LRAG 124 associated reachability does not receive any updated information. 基于更新后的可达性信息132,每个受影响的LRAG 124然后可以并行地、 串行地或以其他合适的方式配置NVE 109中的对应VRT II2。 Up to 132 based on the updated information, each affected LRAG 124 may then be parallel, in series, or arranged in other suitable manner corresponding to the VRT II2 NVE 109. 每个LRAG 124独立于所有其他LRAG 124操作,并且仅负责将可达性信息132传播到被包含在相关联的覆盖分区125中的相关端点。 Each LRAG 124 LRAG 124 independently of all other operations, and is only responsible for propagating reachability information associated endpoint 132 to cover the partition 125 is included in the associated.

[0058] 在某些实施例中,原始LRAG (例如,第一LRAG 124a)还可以配置通过底层网络120 (图2)到目标点的过渡(transition)隧道143的原始点,以减少或甚至避免在重新定位期间的分组丢失。 [0058] In certain embodiments, the original LRAG (e.g., a first LRAG 124a) may also be configured by the underlying network 120 (FIG. 2) to the target point of transition (Transition) tunnel origin point 143 to reduce or even avoid packet loss during repositioning. 目标LRAG 124 (例如,第三LRAG 124c)可以配置过渡隧道的目标端点。 Target LRAG 124 (e.g., third LRAG 124c) may be configured to transition destination endpoint of the tunnel. 过渡隧道可以包括底层网络120的一个或多个网络节点111 (图10),虚拟机114'的配置、数据和/或其他合适的信息可以通过该网络节点111从原始主机(例如,第一服务器102a)被传输到目标主机(例如,第三服务器102c)。 Transition tunnel may include one or more of the underlying network 120 network node 111 (FIG. 10), configure the virtual machine 114 ', data and / or other suitable information through the network node 111 from the original host (e.g., the first server 102a) is transferred to the target host (e.g., the third server 102c). 在其他实施例中,过渡隧道可以由其他合适的实体来建立。 In other embodiments, the transition tunnel may be established by other suitable entity.

[0059] 在一个实施例中,可以预先建立过渡隧道143。 [0059] In one embodiment, transition tunnel 143 may be pre-established. 例如,预先建立的隧道可以包括从原始主机到目标主机的网络路径。 For example, pre-established tunnel may include a network path from the original host to the target host. 该路径建立在底层网络120中的网络节点中的转发表中。 The path is established in the network node 120 in the underlying network forwarding table. 如果底层网络120如图2所示被分层地划分,则可以在底层网络120中遵循例如MPLS协议预先建立从服务器102到任何其他服务器102的过渡隧道。 It is hierarchically split if the underlying network 120 shown in FIG. 2, for example, can follow a pre-established MPLS protocol from the server 102 to any other server 102 in the transition tunnel 120 underlying network. 在一个实施例中,底层网络地址用于标识底层网络120中的期望网络路径。 In one embodiment, the underlying network address for the desired network path 120 identifies the underlying network. 所标识的网络路径可以不同于由对应路由协议计算的最短网络路径。 The network path may be different from the identified shortest path calculated by the corresponding network routing protocol. 在另一实施例中,底层网络地址可以用于标识可以使用的网络路径。 In another embodiment, the underlying network address may identify a network path may be used. 在其他实施例中,租户虚拟网络标识符、租户地址、或底层网络地址中的至少一些的组合可以用于标识底层网络120中的期望网络路径。 In other embodiments, a combination of at least some of the virtual network identifier of the tenant, the tenant address, or the underlying network may be used to address a desired network path 120 identifies the underlying network.

[0060] 当底层网络地址用于标识网络路径时,如果需要,相同的底层网络地址可以标识由底层网络120转发的分组的服务链。 [0060] When the underlying network address identifies a network path, if necessary, the same underlying network address may be identified by the underlying network 120 forwards the packet service chain. 当通过底层网络120传输时,覆盖网络分组可能需要经历一个或多个物理和/或虚拟化网络功能的序列。 When the underlying transport network 120 via the overlay network packets may need to go through a sequence of one or more physical and / or virtual network capabilities. 这样的网络功能的示例可以包括防火墙、名称服务器、负载平衡器和/或其他合适的功能,并且通常被称为服务链。 Examples of such functions may include a network firewall, name servers, the load balancer and / or other suitable functionality, and is generally called a service chain. 因为底层网络地址标识通过底层网络120的特定路径,所以相同的底层网络地址也可以用于选择或标识按照期望序列穿过实现某些网络功能的网络节点的特定路径。 Because the underlying network address identifies a particular path through the underlying network 120, the same underlying network address can also be used to select or identify the desired sequence in accordance with a particular path through the network node to achieve certain network functions.

[0061] 覆盖网络资源管理器126可以确定要用于过渡隧道143的底层网络地址和/或网络路径,并且将底层网络地址和/或网络路径传送到与原始主机相关联的第一LRAG 124a。 [0061] overlay network resource manager 126 may determine the network address for the underlying transition tunnel 143 and / or network path, and the underlying transport network address and / or network path to a first LRAG 124a associated with the original host. 在某些实施例中,覆盖网络资源管理器126可以通过向原始主机传输目标主机的某些可达性信息(例如,其底层网络地址)来标识网络路径。 In certain embodiments, the overlay network resource manager 126 may be identified by some network path to the original host reachability information transmission target host (e.g., the underlying network address). 在其他实施例中,可以以其他合适的方式来标识网络路径。 In other embodiments, other suitable way may be to identify a network path. 一旦底层网络地址和/或网络路径被确定,则在原始主机(例如,第一服务器102a)处的隧道操作可以开始。 Once the underlying network address and / or network path is determined, the original host (e.g., a first server 102a) at the start tunneling. 在某些实施例中,第一服务器102a可以使用底层网络地址来封装与重新定位的虚拟机114'(或VNF)相关联的分组,并且通过底层网络120将封装的分组转发到目标虚拟机114”。因此,可以减少或甚至避免虚拟机重新定位期间的这样的分组丢失。 In certain embodiments, the first server 102a may be used to encapsulate the underlying network addresses relocated VM 114 '(or VNF) associated with the packet, and forwards the encapsulated packet 120 to the target virtual machine 114 through the underlying network . "Thus, it is possible to reduce or even avoid such groups during the virtual machine to re-locate lost.

[0062] 最终,可能不再需要过渡隧道,因为受影响的虚拟网络122 (例如,第一虚拟网络122a)的VRT 112都用新的端点标识符值被独立地更新。 [0062] Finally, the transition may not be required tunnel, because the affected virtual network 122 (e.g., 122a of the first virtual network) VRT 112 independently are updated with the new endpoint identifier value. 因此,到重新定位的虚拟机114'的消息可以被直接传输到目标虚拟机114”。过渡隧道可以包括在原始NVE 109处的虚拟网络122的VRT 112中的条目。因此,可以在选择的时间段之后消除过渡隧道,例如通过使用定时器来消除VRT中的条目112。 Thus, messages to the relocated VM 114 'can be transmitted directly to the target virtual machine 114. "Transition tunnel may include an entry in the VRT virtual network original NVE 109 at 122 to 112. Accordingly, at a selected time after a transition period to eliminate the tunnel, for example, to eliminate the VRT entry 112 by using a timer.

[0063]即使上述虚拟机重新定位仅涉及一个虚拟机114',在其他实施例中,也可以执行大体上类似或相同的操作以在批处理模式下移动多个虚拟机和/或虚拟网络功能。 [0063] Even though the above only relates to reposition the virtual machine a virtual machine 114 ', in other embodiments, may be substantially similar or perform the same operation in batch mode to move the plurality of virtual machines and / or virtual network function . 例如,可以重复上述操作以将多个或所有虚拟机114从一个物理服务器102重新定位到另一物理服务器,从物理位置中的服务器102重新定位到不同物理位置中的服务器1〇2,或者从数据中心中的服务器1〇2重新定位到不同的数据中心的服务器102。 For example, the operation may be repeated a plurality of or to all virtual machines from one physical server 114 102 relocated to another physical server above, from the physical location of the positioning server 102 back to a different physical locations 1〇2 server, or from 1〇2 data center server relocated to a different data center server 102. 在另一示例中,多个或所有虚拟机114可以作为组被关联到物理或虚拟化网络功能,例如软件负载平衡器。 In another example, a plurality or all of the virtual machines 114 may be associated as a group to the physical or virtual network functions, such as software load balancer. 在这样的示例中,如果移动软件负载平衡器,则可能期望将多个或全部关联的虚拟机114与软件负载平衡器一起移动,例如以使虚拟机114保持驻留在物理上接近软件负载均衡器的服务器102中。 In such an example, if the software load balancer movement, it may be desirable to move along a plurality or all of the associated virtual machine software load balancer 114, for example, so that the virtual machine 114 to maintain load balancing software residing in close physical 's server 102. 在其他示例中,可以以其他合适的方式执行上述操作,以实现虚拟机和/或虚拟网络功能的批量重新定位。 In other examples, the above-described operation may be performed in other suitable manner, to achieve a virtual machine, and / or batch virtual networking features repositioned.

[0064]在上面参考图3的描述中,覆盖网络资源管理器1况向个体受影响的LRAG 124传播关于虚拟机114的重新定位的更新后的可达性信息132。 [0064] In the description above with reference to FIG. 3, the cover reachability information network resource manager 1 to the status of the affected individual propagation LRAG 124 updates the virtual machine repositioning 114 132. 然而,在其他实施例中,这样的传播可以通过其他合适的实体来执行。 However, in other embodiments, such a spread may be performed by other suitable entity. 例如,如图4所示,一旦LRAG 124己经配置了托管虚拟机114或虚拟网络功能的适当的服务器102中的VRT 112,则每个LRAG 124可以使用路由协议(例如边界网关协议(“BGP”))向其他LRAG 124通告更新后的可达性信息132。 For example, as shown in FIG. 4, once LRAG 124 has configured the host virtual machine 114 or virtual network functions appropriate server 102 VRT 112, then each LRAG 124 can use a routing protocol (e.g., Border Gateway Protocol ( "BGP ")) announce reachability information 132 updated to other LRAG 124. 在某些实施例中,可以通过在LRAG 124之间使用路由过滤,仅向与覆盖分区125相关联的那些LRAG 124通告新的路由,该覆盖分区1¾包含虚拟机114或虚拟网络功能被附接到的虚拟网络122的端点。 In certain embodiments, the route by using a filter between LRAG 124, a new route to advertise only those LRAG 124 125 coverage associated partition, the partition cover 1¾ comprising a virtual machine or virtual network function 114 are attached end-to-virtual network 122. 原始LRAG 1以(例如,第一LRAG 124a)可以使用例如路由过滤技术(诸如BGP中的路由目标(RT)特征)来确定受到重新定位影响的其他LRAG 124。 LRAG 1 to the original (e.g., a first LRAG 124a) may be used, for example, route filtering techniques (such as feature route target (RT) BGP in) is determined by the influence of other repositioning LRAG 124. 原始LRAG 124然后可以将更新后的可达性信息132传输到那些受影响的LRAG 124。 Original LRAG 124 reachability information may then be updated 132 to transmit those affected LRAG 124. 每个LRAG 124还可以向包含虚拟机114或虚拟网络功能被附接到的虚拟网络122的端点(如果有的话)的对应覆盖分区125中的其他NVE 109通告新的可达性信息。 Each LRAG 124 may further comprise an endpoint to a new reachability information (if any) corresponding to coverage other partitions NVE 109 125 114 advertise a virtual machine or virtual network function is attached to the virtual network 122. NVE 109可以作为客户端逻辑地互连到对应LRAG 124,并且LRAG 124可以仅基于路由过滤或其他合适的技术来通告路由。 NVE 109 can serve as client logic interconnected to a corresponding LRAG 124, and may only be LRAG 124 based routing filtration or other suitable technique advertised route. 在其他实施例中,原始LRAG 124可以向所有其他LRAG 124广播更新后的可达性信息1幻。 In other embodiments, the original phantom LRAG 124 may reachability information to all other LRAG 124 broadcasts the updated one. 反过来,其他LRAG 124可以单独地确定更新后的可达性信息132是否影响对应覆盖分区125中包含的任何端点。 In turn, other LRAG 124 may individually determine reachability information 132 updated affect any end cover corresponding to the partition 125 contains. 基于该确定,其他LRAG 124可以相应地更新对应VRT 112和/或NVE 109 (图1)。 Based on this determination, other LRAG 124 may update the corresponding VRT 112 and / or NVE 109 (FIG. 1).

[0065]在图1-4中,每个服务器1〇2被示出为在具有对应LRAG 124的对应覆盖分区125中。 [0065] In FIGS. 1-4, each server 1〇2 is shown having a corresponding coverage LRAG 124 corresponding to the partition 125. 然而,如上所述,覆盖分区125可以在其他合适的基础上被划分。 However, as described above, to cover the partition 125 may be divided in other suitable basis. 例如,如图5所示,第一覆盖分区125a可以包括与第一服务器102a和第三服务器l〇2c二者互连的第一LRAG 124a。 For example, as shown in Figure 5, the first cover 125a may include a first partition LRAG 124a interconnected with both the first server and the third server l〇2c 102a. 第二覆盖分区125b可以包括互连到第二服务器102b的第二LRAG 1Mb。 The second cover may comprise a partition 125b interconnected to a second LRAG 1Mb a second server 102b. 在另外的实施例中,服务器102和/或LRAG 1M可以具有其他合适的布置和/或配置。 In further embodiments, the server 102 and / or LRAG 1M may have other suitable arrangements and / or configurations. 即使上面在覆盖分区125的上下文中描述了参考图3_5的虚拟机114的迁移,在其他实施例中,上述使用过渡隧道143的迀移技术也可以在不包括被分区的覆盖网络、包括部分被分区的覆盖网络、或者包括覆盖和/或底层网络中的其他合适的布置的计算机网络中实现。 Even described above in the context of covering the partition 125 is described migration with reference to FIG virtual machine 3_5 114, in other embodiments, the use of a transition tunnel 143 Gan shifting techniques may not include partition overlay network, comprising a portion overlay network partition, or other computer network comprising a suitable arrangement of the cover and / or the underlying network implementation.

[0066]图6是示出根据所公开的技术的实施例的适用于图1的计算机网络1〇〇的LRAG 124 的示例软件部件的框图。 [0066] FIG. 6 is a block diagram applicable to the embodiment of FIG. 1 illustrating techniques in accordance with the disclosed computer network LRAG exemplary software components 124 of the 1〇〇. 如图6所示,LRAG 1¾可以包括彼此互连的配置部件142、控制部件144和可选的更新部件146。 As shown in FIG 6, LRAG 1¾ another configuration may include an interconnection member 142, and the control section 144 updates the optional member 146. 部件142、144和146中的每个可以是以常规编程语言作为源代码编写的计算机程序、过程或例程,或者一个或多个模块可以是硬件模块。 Computer program means 142, 144 and 146 each may be a conventional source code written in a programming language, processes, or routines, or modules may be one or more hardware modules. 即使在图6中仅示出了前述部件,在其他实施例中,LRAG 124也可以包括输入部件、输出部件、网络部件和/或其他合适部件中的一个或多个。 Even in FIG. 6 shows only the components, in other embodiments, LRAG 124 may also include one or more input member, an output member, network components, and / or other suitable components.

[0067] 配置部件142可以被配置为基于从覆盖网络资源管理器126接收的可达性信息132 来填充、更新和/或以其他方式管理对应覆盖分区125(图1)中的VRT 112。 [0067] The configuration component 142 may be configured based on the accessibility information received from the resource manager 126 overlay network 132 is filled, update and / or otherwise manage the corresponding VRT partition cover 125 (FIG. 1) 112. 例如,如图6所示, 配置部件142可以基于可达性信息132中的网络节点的映射来生成、更新或以其他方式管理VRT 112中的转发表148中的条目。 For example, as shown in FIG. 6, the configuration component 142 may be based on the mapping of the network nodes in the reachability information 132 to generate, update, or otherwise manage 148 entries in the forwarding VRT 112. 在某些实施例中,转发表148中的条目可以单独地包括源网络节点的源地址、目的地网络节点的目的地地址、和/或经由例如图2的底层网络120在源和目的地网络节点之间的一个或多个网络路径。 In certain embodiments, the entries in the forwarding table 148 may individually comprise a destination address a source address of a source network node, the destination network node, and / or via e.g. FIG. 2 of the underlying network 120 in the source and destination networks one or more paths between network nodes. 在其他实施例中,转发表148中的条目可以包括网络节点111 (图2)的标识、边缘节点137 (图2)的标识、域133或135 (图2)的标识、和/或形成从源到目的地网络节点的路由的至少一部分的其他合适的网络实体的标识。 In other embodiments, the forwarding table 148 entry may include identifying the network node 111 (FIG. 2), the edge node 137 (FIG. 2) of the identification field 133 or 135 (FIG. 2) of identification and / or formed from other suitable network entity identification of the source of at least a portion of the route to the destination network node.

[0068] 控制部件144可以被配置为在管理虚拟机114时控制管理程序107。 [0068] The control unit 144 may be configured to control management program 107 when the management virtual machine 114. 例如,在一个实施例中,控制部件144可以指令管理程序107实例化新的虚拟机114,并且基于所接收的可达性信息132来将实例化的虚拟机114附接到虚拟网络122 (图1)。 For example, in one embodiment, the control unit 144 may instruct the management program 107 instantiates a new virtual machine 114, and reachability information 132 based on the received instance of the virtual machine 114 is attached to the virtual network 122 (FIG. 1). 在另一示例中,控制部件144 可以指令管理程序107基于所接收的可达性信息132来暂停、终止和/或以其他方式操纵虚拟机114中的一个。 In another example, the control unit 144 may instruct to suspend the hypervisor 107 reachability information 132 based on the received termination and / or manipulation of a virtual machine 114 in other ways. 在另外的示例中,控制部件144可以使管理程序107执行前述操作和/或其他合适的操作的组合。 In a further example, the control section 144 may cause the hypervisor 107 performs operations and combinations of the foregoing and / or other suitable operations.

[0069]在一个实施例中,更新部件146可以被配置为向覆盖网络资源管理器126提供状态通知134。 [0069] In one embodiment, the updating component 146 may be configured to notify the overlay network 134 to the resource manager 126 provides status. 状态通知134可以包括向覆盖网络资源管理器126通知关于实例化、暂停、终止和/ 或与虚拟机114相关的其他合适的操作的完成的信息。 State notification 134 may include a notification 126 to the overlay network resource manager is instantiated on, pause, other suitable information to complete an operation relating to termination 114 and / or virtual machines. 在其他实施例中,更新部件146还可以向其他LRAG 124'(为了清楚起见以虚线示出)通告更新后的可达性信息132。 In other embodiments, member 146 may also be updated 124 '(for clarity shown in phantom) to other LRAG reachability information update notice 132.

[0070]在操作中,覆盖网络资源管理器126可以将可达性信息132传输到LRAG 124。 [0070] In operation, the overlay network resource manager 126 may transmit the reachability information 132 to LRAG 124. 基于所接收的可达性信息132,配置部件142可以配置VRT 112中的转发表148。 Reachability information 132 based on the received configuration component 142 can configure the forwarding VRT 112 148. 在某些实施例中, 控制部件144还可以基于所接收的可达性信息132来实例化、暂停、终止或以其他方式操纵在服务器102上托管的虚拟机114中的一个或多个。 In certain embodiments, the control member 144 may also be based on accessibility information 132 of the received instances, suspend, terminate, or otherwise manipulate one or more servers 102 on a hosted virtual machine 114. 一旦控制部件144完成对虚拟机114的操纵,更新部件146可以向覆盖网络资源管理器126传输状态通知134以向其通知完成。 Upon completion of manipulation of the control section 144 of virtual machine 114, the updating component 146 can notify the transmit state 126 the overlay network resource manager 134 to complete its notification. 作为响应,在某些实施例中,覆盖网络资源管理器126然后可以将更新后的可达性信息132传输到其他受影响的LRAG 124'。 In response, in certain embodiments, the overlay network resource manager 126 may then transmit the reachability information 132 after update to other affected LRAG 124 '. 在其他实施例中,LRAG 124可以直接向其他LRAG 124'通告更新后的可达性信息132。 In other embodiments, LRAG 124 directly to other LRAG 124 'advertise reachability information 132 updated.

[0071]图7是示出根据所公开的技术的实施例的更新图1的计算机网络1〇〇中的可达性信息的过程2〇〇的流程图。 [0071] FIG. 7 is a flowchart showing a process of a computer network in 2〇〇 1〇〇 updated view of an embodiment of the disclosed technique. 1 reachability information. 如图7所示,过程200可以包括在阶段202接收可达性信息。 As shown in FIG. 7, process 200 may include receiving 202 at stage reachability information. 在一个实施例中,可以从包含虚拟和对应物理网络节点之间的映射的记录的数据库接收可达性信息。 In one embodiment, the reachability information may be received from a database containing records a mapping between the virtual and corresponding physical network nodes. 在其他实施例中,可以以其他合适的方式获得可达性信息。 In other embodiments, the reachability information can be obtained in other suitable manner.

[0072]在某些实施例中,过程2〇0可以包括可选的阶段204,在可选的阶段204中,确定覆盖网络的每个覆盖分区的合适的可达性信息的子集。 [0072] In certain embodiments, the process may include an optional 2〇0 stage 204, in optional stage 204, to determine the appropriate subset for each partition cover reachability information overlay network. 在一个实施例中,可达性信息的子集包括与包括对应覆盖分区中的至少一个端点的一个或多个虚拟网络相关的可达性信息。 In one embodiment, a subset of the reachability information includes reachability information associated with the cover comprises a partition corresponding to the at least one endpoint of one or more virtual networks. 对于不包括对应覆盖分区中的至少一个端点的一个或多个虚拟网络,与这样的一个或多个虚拟网络相关的可达性信息从子集中被排除。 Does not correspond to the cover comprises at least one endpoint of the partition one or more virtual networks, reachability information associated with such one or more virtual networks are excluded from the subset. 过程200然后可以包括在阶段206将所确定的合适的可达性信息传输到每个覆盖分区中的LRAG。 Process 200 may then comprise a suitable transmission 206 reachability information to each of the determined partition LRAG covering stage. 作为响应,每个覆盖分区中的LRAG然后可以更新与具有特定覆盖分区中的至少一个端点的虚拟网络相关的一个或多个虚拟路由表。 In response, each of the partition cover may then update LRAG having at least one endpoint associated with a particular virtual partition covers or more virtual network routing tables. 在其他实施例中,可以省略可选的阶段204,并且可以向所有覆盖分区传输相同的可达性信息。 In other embodiments, optional stage 204 may be omitted, and may be identical to cover all partitions reachability information transmission. 作为响应,每个覆盖分区可以确定具有每个覆盖分区中的至少一个端点的虚拟网络的可达性信息的子集。 In response, each cover having a partition may be determined subset of reachability information each partition covering at least one endpoint of the virtual network. 在其他实施例中,每个LRAG可以订阅例如图1的覆盖网络资源管理器126,用于接收与一个或多个虚拟网络相对应的合适的可达性信息。 In other embodiments, each of the overlay network e.g. LRAG can subscribe to resource manager 126 of FIG. 1, suitable for receiving the reachability information with one or more corresponding virtual network. 在另外的实施例中,可以利用削述确定操作的组合,例如,通过在传输之前确定第一子集并且在每个覆盖分区从第一子集确定第二子集。 In further embodiments, said determining operation may be utilized to cut a combination, for example, and determining a second subset from the first subset by determining a first subset prior to transmitting each partition cover. 过程200还可以包括在阶段2〇s更新可达性信息,如下面参考图8更详细地描述的。 Process 200 may further include updating reachability information in 2〇s stage, as described in more detail below with reference to FIG.

[0073]图8是示出根据所公开的技术的实施例的更新图丨的计算机网络丨〇〇中的可达性信息的过程220的流程图。 [0073] FIG 8 is a flowchart 220 illustrating a process of updating the computer network of FIG Shu Shu thousand and embodiments of the disclosed technology reachability information. 如图8所示,过程200可以包括在阶段222从一个或多个覆盖分区接收一个或多个状态更新。 8, process 200 may include receiving updates from a stage 222 covers one or more partitions or more states. 更新可以包括实例化、开始、暂停、终止和/或虚拟机和/或虚拟网络功能的其他合适的操作中的一个或多个的完成通知。 Update may include instantiating, start, pause, terminate, and / or virtual machine and the completion notification / or one or more other suitable operating functions of the virtual network. 过程220然后可以包括确定受到所接收的一个或多个状态更新影响的一个或多个其他覆盖分区。 Process 220 then may include one or more state determined by the received updates affect one or more other partitions covered. 在一个实施例中,如果覆盖分区包括具有受到一个或多个更新影响的至少一个端点的虚拟网络,则覆盖分区受到影响。 In one embodiment, if the cover comprises a partition having subjected to one or more virtual network at least one endpoint update impact, the partition covering affected. 在其他实施例中,可以基于其他合适的标准来确定受影响的覆盖分区。 In other embodiments, it may be determined to cover the affected partition based on other suitable criteria. 过程22〇然后可以包括在阶段226将一个或多个可达性更新仅传输到受影响的一个或多个覆盖分区。 Process 22〇 then at stage 226 may include one or more transmitting reachability updates only to the affected one or more cover partitions. 未受影响的其他覆盖分区不接收一个或多个可达性更新。 Other coverage unaffected partition does not receive one or more reachability updates.

[0074]图9是示出根据所公开的技术的实施例的管理覆盖分区中的可达性信息的过程300的流程图。 [0074] FIG. 9 is a flowchart showing process management 300 according to an embodiment of the disclosed technique to cover up the partition information. 如图9所示,过程3〇〇包括在阶段3〇2接收可达性信息。 9, the process comprising 3〇2 3〇〇 reachability information received at stage. 所接收的可达性信息仅针对具有覆盖分区中的至少一个端点的虚拟网络。 Reachability information received only for the partition that covers at least one endpoint of the virtual network. 过程3〇〇然后可以包括在阶段304为覆盖分区中的虚拟网络配置虚拟路由表。 3〇〇 process may then include a virtual routing table configured to cover a partition stage 304 in the virtual network. 可选地,过程300还可以包括向图1的覆盖网络资源管理器1%、其他覆盖分区(未示出)、和/或其他合适的实体通告可达性更新。 Alternatively, the process 300 may also include overlay network resource manager 1% to FIG. 1, other partition covers (not shown), and / or other suitable entity advertised reachability updates.

[0075]图10是示出根据所公开的技术的实施例的管理覆盖分区中的可达性信息的另一过程301的流程图。 [0075] FIG. 10 is a flowchart showing process management 301 according to another embodiment of the disclosed technique to cover the partitions reachability information. 除了过程301包括在阶段303确定针对当前覆盖分区的合适的可达性信息之外,过程301的操作可以大体上类似于图9中的过程3〇〇的操作。 In addition the process 303 determines at stage 301 comprises suitable for reachability information outside the current coverage partition, operation of the process 301 may be substantially similar to the operation in FIG. 9 3〇〇 the process. 合适的可达性信息可以包括仅与具有覆盖分区中的至少一个端点的虚拟网络相关的信息。 Suitable reachability information may include only the virtual network associated with the cover having at least one end of the partition information. 在其他实施例中,过程301还可以包括确定针对其他覆盖分区的合适的可达性信息,并且遵循例如合适的路由协议传播所确定的合适的可达性信息。 In other embodiments, the process 301 may also include a suitable cover reachability information for the other partitions to determine, for example, follow the appropriate routing and protocol suitable propagating reachability information determined.

[0076]图11是示出根据所公开的技术的实施例的重新定位虚拟租户端点(“TEP”)的过程400的流程图。 [0076] FIG. 11 is a flowchart illustrating an embodiment of repositioning the art according to the disclosed tenant virtual endpoint ( "TEP") process 400. 如图11所示,过程400包括在阶段402接收重新定位原始TEP的指示。 11, the process 400 includes receiving an indication in the repositioning of the original stage 402 TEP. 原始TEP 可以包括虚拟机、虚拟网络功能和/或其他合适的实体。 Original TEP may include a virtual machine, the virtual network functions and / or other suitable entity. 过程400然后可以包括在阶段404准备目标TEP。 Process 400 then may include preparing the stage target TEP 404. 可以通过实例化、开始和/或以其他方式生成附接到包含原始TEP的虚拟网络的目标TEP来准备目标TEP。 It can be instantiated, the start and / or otherwise attached to the generated virtual network containing the original target of TEP TEP TEP to prepare a target. 过程400可以包括确定目标TEP是否准备好的判定阶段406。 Process 400 may include determining whether the target TEP ready for adjudication phase 406. 如果目标TEP未准备好,则过程400在阶段404回复到准备目标TEP。 If the target TEP is not ready, the process reverts to 400 in stage 404 ready target TEP.

[0077] 如果目标TEP准备好,则过程400进行到在阶段408在原始和目标TEP之间建立隧道。 [0077] If the target TEP is ready, the process 400 proceeds to build a tunnel between the original stage 408 and the target TEP. 在某些实施例中,可以例如通过预先确定与原始和目标TEP相对应的网络节点之间的一个或多个网络路径来预先建立隧道。 In certain embodiments, for example, by one or more predetermined network path between the origin and destination network nodes TEP corresponding to pre-established tunnel. 例如,可以基于根据MPLS协议托管目标TEP的网络节点的网络地址来预先确定隧道。 For example, the tunnel may be predetermined based on the network address of the TEP based on the target managed network nodes MPLS protocol. 在其他实施例中,可以通过例如基于原始和/或目标TEP地址计算网络路径来在自组织基础上建立隧道。 In other embodiments, the tunnel may be established on the basis of the ad-hoc network path is calculated by, for example based on the raw and / or destination address of the TEP.

[0078] 过程400然后可以包括在阶段410经由隧道将原始TEP重新定位到目标TEP。 [0078] Process 400 may then be included in the original stage 410 via a tunnel to reposition the target TEP TEP. 在一个实施例中,将原始TEP重新定位到目标TEP可以包括虚拟机的热、暖或冷迀移。 In one embodiment, the original target TEP TEP relocated to a virtual machine may include heat, cold or warm Gan shift. 在其他实施例中,重新定位可以包括其他合适类型的迁移。 In other embodiments, repositioning may include other suitable type of migration. 过程400还可以包括在阶段412将重新定位的原始TEP的可达性信息更新到其他覆盖分区。 Process 400 may further comprise 412 to reposition the reachability information update to the original TEP partition cover other stage. 在某些实施例中,通过与目标TEP相关联的覆盖分区中的LRAG,通过图1的覆盖网络资源管理器126、上述部件的组合、或者计算机网络100 (图1)的其他合适的部件,仅将更新后的可达性信息传输到具有包含原始TEP的虚拟网络的至少一个端点的其他覆盖分区。 In certain embodiments, by covering the target partition with the TEP associated LRAG, 126, a combination of the above components, or the computer network 100 (FIG. 1) by means of other suitable overlay network resource manager of FIG. 1, only the reachability information transmission updated to include the original TEP has a virtual network of other partitions covering at least one endpoint. 在其他实施例中,将更新后的可达性信息传输到所有其他覆盖分区。 In other embodiments, the updated reachability information transmitted to all the other coverage partitions. 过程400然后包括在阶段416独立地更新具有包含原始TEP的虚拟网络的至少一个端点的每个虚拟分区中的虚拟路由表。 The process 400 then comprises 416 independently updating each virtual partition has a virtual network containing the original TEP of at least one endpoint of a virtual stage routing table.

[0079] 过程400还可以包括在阶段414在至少一段时间经由所建立的隧道将去往原始TEP 的通信转发到目标TEP,并且在时间段已经期满之后终止转发。 [0079] Process 400 may further include forwarding at least a time stage 414 via the established tunnel communication destined to the original target TEP TEP, and terminates forward after the time period has expired. 在所示实施例中,阶段410、 412和414被示出为彼此平行。 In the illustrated embodiment, stage 410, 412 and 414 are shown as parallel to each other. 在其他实施例中,上述操作可以以串行或其他合适的方式执行。 In other embodiments the operations may be executed in serial or other suitable manner.

[0080]图12是适用于图1中的计算机网络100的某些部件的计算设备600。 [0080] FIG. 12 is a computing device suitable for use in some of the components in FIG. 1 100 600 of the computer network. 例如,计算设备600可以适用于图1的服务器102、覆盖网络资源管理器126或LRAG 124。 For example, computing device 600 may be adapted to the server 102 of FIG. 1, the overlay network resource manager 126 or LRAG 124. 在非常基本的配置602中,计算设备600通常包括一个或多个处理器604和系统存储器606。 In a very basic configuration 602, computing device 600 typically includes one or more processors 604 and system memory 606. 存储器总线608可以用于在处理器604和系统存储器606之间通信。 The memory bus 608 may be used for communication between the processor 604 and system memory 606.

[0081]取决于所期望的配置,处理器604可以是任何类型,包括但不限于微处理器OiP)、 微控制器(yC)、数字信号处理器(DSP)或其任何组合。 [0081] Depending on the desired configuration, processor 604 may be any type, including but not limited to a microprocessor OIP), the microcontroller (yC), a digital signal processor (DSP), or any combination thereof. 处理器604可以包括一个或多个级别的高速缓存(诸如一级高速缓存610和二级高速缓存612)、处理器核614和寄存器616。 The processor 604 may include one or more levels of cache (such as a cache 610 and a level two cache 612), a processor core 614, and registers 616. 示例处理器核614可以包括算术逻辑单元(ALU)、浮点单元(FPU)、数字信号处理核(DSP核)或其任何组合。 An example processor core 614 may include an arithmetic logic unit (ALU), a floating point unit (FPU), a digital signal processing core (DSP Core), or any combination thereof. 示例存储器控制器618也可以与处理器604—起使用,或者在一些实现中,存储器控制器618可以是处理器604的内部部分。 An example memory controller 618 may also be used together with the processor 604-, or in some implementations memory controller 618 may be an internal part of the processor 604.

[0082]取决于所期望的配置,系统存储器606可以是任何类型,包括但不限于易失性存储器(诸如RAM)、非易失性存储器(诸如ROM、闪存等)或其任何组合。 [0082] Depending on the desired configuration, system memory 606 may be any type, including but not limited to volatile memory (such as RAM), nonvolatile memory (such as ROM, flash memory, etc.) or any combination thereof. 系统存储器606可以包括操作系统620、一个或多个应用622、和程序数据624。 The system memory 606 may include an operating system 620, or a 622, and program data over 624 applications. 如图12所示,操作系统620可以包括用于管理一个或多个虚拟机114的管理程序107。 12, the operating system 620 may include one or more managing hypervisor 114 107. 所描述的基本配置602在图12中由内部虚线内的那些部件示出。 Described basic configuration 602 is illustrated by those components within the inner dashed line 12 in FIG.

[0083]计算设备600可以具有附加的特征或功能以及附加的接口,以支持在基本配置6〇2 和任何其他设备和接口之间的通信。 [0083] Computing device 600 may have additional features or functionality, and additional interfaces to support communications between the basic configuration 6〇2 and any other devices and interfaces. 例如,总线/接口控制器630可以用于支持经由存储接口总线6¾的基本配置6〇2和一个或多个数据存储设备632之间的通信。 For example, a bus / interface controller 630 may be used to support communications between the basic configuration 6〇2 and one or more data storage devices 632 via a storage interface bus 6¾. 数据存储设备632可以是可移除存储设备⑽6、不可移除的存储设备638或其组合。 The data storage device 632 may be removable storage devices ⑽6, non-removable storage devices 638, or combinations thereof. 可移除存储设备和不可移除存储设备的示例包括诸如软盘驱动器和硬盘驱动器(HDD)的磁盘设备、诸如压缩盘(CD)驱动器或数字通用盘(DVD)驱动器的光盘驱动器、固态驱动器(SSD)和磁带驱动器等。 Removable storage devices and exemplary non-removable storage devices include such as a floppy disk drive and a hard disk drive (HDD), a magnetic disk device, such as a compact disk (CD) optical disk drive drives or digital versatile disk (DVD) drives, solid state drives (SSD ), and tape drives. 示例计算机存储介质可以包括以用于存储诸如计算机可读指令、数据结构、程序模块或其他数据的信息的任何方法或技术实现的易失性和非易失性、可移除和不可移除介质。 Example computer storage media may include volatile and nonvolatile memory such as computer readable instructions for any method or technology data structures, program modules or other data information is implemented, removable and non-removable media . 术语“计算机可读存储介质”或“计算机可读存储设备”排除传播的信号和通信介质。 The term "computer-readable storage medium" or "computer-readable storage device" exclude propagating signals and communication media.

[0084]系统存储器606、可移除存储设备636和不可移除存储设备638是计算机可读存储介质的示例。 [0084] System memory 606, removable storage 636 and non-removable storage devices 638 are examples of computer-readable storage medium. 计算机可读存储介质包括但不限于1^^、1?01!3£?1?011、闪存或其他存储器技术、 CD-ROM、数字通用盘(DVD)或其他光学存储装置、磁带盒、磁带、磁盘存储装置或其他磁存储设备、或者可以用于存储所需信息并且可以由计算设备600访问的任何其他介质。 The computer-readable storage media include, but are not limited to 1 ^^, 1? 01! 3 £? 1? 011, flash memory or other memory technology, CD-ROM, digital versatile disks (DVD) or other optical storage, magnetic cassettes, magnetic tape , magnetic disk storage or other magnetic storage devices, or may be used to store the desired information and which can be accessed by computing device 600 of any other medium. 任何这样的计算机可读存储介质可以是计算设备600的一部分。 Any such computer readable storage media may be part of computing device 600. 术语“计算机可读存储介质,,不包括传播的信号和通信介质。 The term "computer-readable storage medium ,, not include a signal propagation and communication media.

[0085]计算设备6〇〇还可以包括用于支持经由总线/接口控制器630的从各种接口设备、列如」棚m攻侖M厶外围议备接口644和通信设备646)到基本配置602的通信的接口总线640。 [0085] The computing device may further comprise a supporting 6〇〇 via the bus / interface controller interfaces from a variety of devices, such as a column "m shed M Lun Si attack peripheral interfaces 644 and Discussion Preparation communication device 646) to basic configuration 630 602 communication interface bus 640. 示例输出设备糾2包括图形处理单元6仙和音频处理单元65〇,其可以被配置为经由一个或多个A/_V端口652与诸如显示器或扬声器的各种外部设备通信。 Examples of output devices include a graphics processing unit 2 correction $ 0.06 and an audio processing unit 65〇, which may be configured to communicate via one or more A / _V port 652 such as a display or a speaker with various external devices. 示例性外围设备接口644包括串行接口控制器654或并行接口控制器656,其可以被配置为经由一个或多个1/〇端口6明与诸如输入设备(例如,键盘、鼠标、笔、语音输入设备、触摸输入设备等)或其他外围设备(例如,打印机、扫描仪等)的外部设备通信。 Exemplary peripheral interfaces 644 include a serial interface controller 654 or a parallel interface to the controller 656, which may be configured via one or more of 1 / out port 6 such as a square input devices (e.g., keyboard, mouse, pen, voice communication with external devices input device, touch input device, etc.) or other peripheral devices (e.g., printer, scanner, etc.). 示例通信设备646包括网络控制器66〇,其可以被布置为支持经由一个或多个通信端口664通过网络通信链路的与一个或多个其他计算设备662的通信。 An example communication device 646 includes a network controller 66〇, which may be arranged to support communication through one or more other computing devices 662 of the network communication link via one or more communication ports 664.

[0086]网络通信链路可以是通信介质的一个示例。 [0086] network communication link may be one example of communication media. 通信介质通常可以通过计算机可读指令、数据结构、程序模块或调制数据信号(例如载波或其他传输机制)中的其他数据来实现, 并且可以包括任何信息传递介质。 Communication media may typically be a computer-readable instructions, data structures, program modules, or other data in a modulated data signal (e.g., carrier wave or other transport mechanism) is implemented, and may include any information delivery media. “调制的数据信号”可以是以能够在信号中编码信息的方式设置或改变其一个或多个特性的信号。 "Modulated data signal" may be a signal capable of setting or changing one or more characteristics of the signal in a manner as to encode information. 作为示例而非限制,通信介质可以包括诸如有线网络或直接有线连接的有线介质以及诸如声学、射频(RF)、微波、红外(IR)和其他无线介质的无线介质。 By way of example and not limitation, communication media may include wired media such as a wired network or direct-wired media wired connection such as acoustic, radio frequency (RF), microwave, infrared (IR) and other wireless media. 如本文中所使用的术语计算机可读介质可以包括存储介质和通信介质两者。 As used herein, the term computer readable media may include both storage media and communication media. [0087]计算设备6〇0可以被实现为小型便携式(或移动)电子设备的一部分,电子设备诸如蜂窝电话、个人数字助理(PDA)、个人媒体播放器设备、无线网络手表设备、个人头戴式耳机设备、专用设备、或包括任何上述功能的混合设备。 Part [0087] 6〇0 computing device may be implemented as a small form factor portable (or mobile) electronic device, an electronic device such as a cellular phone, a personal digital assistant (PDA), a personal media player device, a wireless network watch device, a personal headset type headphone device, an application specific device, or a hybrid device that include any of the above functions. 计算设备600还可以被实现为包括膝上型计算机和非膝上型计算机配置二者的个人计算机。 Computing device 600 may also be configured to achieve both the personal computer including both laptop computer and non-laptop computer.

[0088]上面已经出于说明的目的描述了本技术的具体实施例。 [0088] have been described above specific embodiments of the present technology is for purposes of illustration. 然而,在不脱离前述公开的情况下可以进行各种修改。 However, in the foregoing without departing from the disclosure may be variously modified. 另外,除了或替代其他实施例的元件,一个实施例的很多元件可以与其他实施例组合。 In addition to or instead of other embodiments of the elements, a lot of element embodiment may be combinable with embodiments other embodiments. 因此,除了所附权利要求之外,本技术不受限制。 Thus, in addition to other than the appended claims, the present technology is not limited.

Claims (10)

  1. 1.一种具有处理器和耦合至所述处理器的存储器的计算系统,所述存储器包含在由所述处理器执行时引起所述处理器执行方法的指令,所述方法包括: 接收与具有覆盖网络的计算机网络中的覆盖分区相关的可达性信息集合,所述覆盖网络在逻辑上被划分为多个覆盖分区并且在底层网络上被实现,其中所述可达性信息包括所述覆盖分区中的一个或多个虚拟端点到所述虚拟端点当前驻留的所述底层网络中的网络节点的映射,并且其中所述可达性信息集合仅与一个或多个虚拟网络相关,所述一个或多个虚拟网络具有所述覆盖分区中的至少一个虚拟端点;以及基于所接收的所述可达性信息来配置具有所述覆盖分区中的至少一个虚拟端点的所述一个或多个虚拟网络的虚拟路由表,使得所述虚拟网络中的每个虚拟网络独立于其他虚拟网络来执行可达性更新。 A having a processor and a processor coupled to the computing system memory, the memory containing instructions to cause the processor to perform a method when executed by the processor, the method comprising: receiving with overlay overlay networks in a computer network reachability information associated with a set of partitions, the overlay network is logically divided into a plurality of partitions cover and is implemented on the underlying network, wherein the reachability information comprises a cover a plurality of partitions or virtual endpoint to the virtual network endpoint map the underlying network node currently resides, and wherein the reachability information set associated with only one or more virtual networks, the one or more virtual network having at least one virtual partition end of the cover; and based on the received accessibility information to configure the cover having at least one virtual partition endpoint of one or more virtual virtual network routing table, such that the virtual network for each virtual network in the virtual network independently of the other to perform the reachability updates.
  2. 2. 根据权利要求1所述的计算系统,其中配置所述虚拟路由表包括配置针对具有所述覆盖分区中的至少一个虚拟端点的所述一个或多个虚拟网络中的每个虚拟网络的转发表。 2. The computing system of claim 1, wherein configuring comprises configuring the virtual route forwarding table for the one or more virtual network having at least one virtual partition covering the end of each of the virtual network published.
  3. 3. 根据权利要求1所述的计算系统,其中配置所述虚拟路由表包括生成所述虚拟路由表中的条目,所述条目具有所述虚拟网络中的一个虚拟网络中的目的地虚拟端点的IP地址以及所述目的地虚拟端点当前驻留的所述底层网络中的网络节点的标识符。 3. The computing system of claim 1, wherein configuring the virtual routing table comprises generating a virtual entries in the routing table, the entries in the virtual network having a virtual network endpoint destination virtual IP address and the destination virtual network node endpoint identifier of the underlying network currently camped.
  4. 4. 一种由具有处理器的计算设备执行的方法,所述方法包括: 通过所述处理器, 确定针对具有覆盖网络的计算机网络中的个体覆盖分区的可达性信息集合,所述覆盖网络在底层网络上被实现,所述可达性信息包括虚拟端点到所述虚拟端点当前驻留的所述底层网络中的网络节点的地址的映射,其中所确定的所述可达性信息集合与一个或多个虚拟网络相关,所述一个或多个虚拟网络具有所述覆盖分区中的一个覆盖分区中的至少一个虚拟端点;以及向所述个体覆盖分区传输所确定的所述可达性信息集合,使得所述覆盖分区中的每个覆盖分区独立于其他覆盖分区来执行可达性更新。 4. A method performed by a computing device having a processor, the method comprising: the processor determines the reachability information for the individual partition covering a computer network having a set of overlay network, the overlay network is implemented on the underlying network, the reachability information includes a virtual end-to-end mapping of the virtual addresses of the underlying network currently residing in a network node, wherein the reachability information set and determined related to one or more virtual networks, the one or more virtual network having a virtual endpoint of said at least one cover covering the partition partition; covering said partition transmitting reachability information of the determined subject to the set, so that the covering covers each partition independent of the other partitions to perform the partitioning cover reachability updates.
  5. 5.根据权利要求4所述的方法,其中: 所述底层网络包括多个网络节点以及通过所述网络节点互连的服务器;以及所述覆盖分区是所述覆盖网络的逻辑分区,所述覆盖网络基于所述底层网络中的所述服务器、所述虚拟网络或所述虚拟端点中的至少一个被划分。 5. The method of claim 4, wherein: the bottom layer comprises a plurality of network nodes and network nodes interconnected by said network server; and covering said partition is a logical partition of the network coverage, the cover the network is based on the underlying network server, the network is divided into at least one virtual or virtual endpoints.
  6. 6.根据权利要求4所述的方法,其中: 所述底层网络包括多个网络节点以及通过所述网络节点互连的服务器; 所述虚拟网络中的一个虚拟网络包括被托管在不同的服务器上并且通过所述虚拟网络互连的多个虚拟端点;以及所确定的所述可达性信息集合与托管所述虚拟网络上的所述虚拟端点中的至少一个虚拟端点的服务器相关。 6. The method according to claim 4, wherein: said underlying network comprises a plurality of network nodes and server nodes interconnected via said network; said virtual network includes a virtual network hosted on different servers and a plurality of virtual endpoints of the virtual network interconnection; the upper and the determined set of reachability information with the virtual network hosted at least one virtual terminal server associated virtual endpoint.
  7. 7.根据权利要求4所述的方法,其中: 所述覆盖分区中的每个覆盖分区包括本地可达性接入网关(“LRAG”);以及传输所确定的所述可达性信息集合包括向与所述覆盖分区中的每个覆盖分区相对应的所述LRAG传输所确定的所述可达性信息集合,其中所述LRAG被配置为基于所述可达性信息集合来配置针对所述虚拟网络中的一个或多个虚拟网络的虚拟路由表,每个虚拟网络具有对应覆盖分区中的至少一个虚拟端点。 7. The method as claimed in claim 4, wherein: each of said partition covering the partition cover includes a local reachability access gateway ( "LRAG"); and said transmitting reachability information of the determined set comprises and to the corresponding transmission LRAG the determined set of reachability information for each partition cover covering the partition, wherein the LRAG is configured based on the reachability information for the set of configuration the virtual network to one or more virtual network virtual routing table, each virtual network having a virtual endpoints corresponding to at least cover the partition.
  8. 8. 根据权利要求4所述的方法,其中: 所述覆盖分区中的每个覆盖分区包括本地可达性接入网关(“LRAG”);以及传输所确定的所述可达性信息集合包括向与所述覆盖分区中的每个覆盖分区相对应的所述LRAG传输所确定的所述可达性信息集合,其中所述LRAG被配置为基于所述可达性信息集合来实例化至少一个虚拟端点。 8. The method as claimed in claim 4, wherein: each of said partition covering the partition cover includes a local reachability access gateway ( "LRAG"); and said transmitting reachability information of the determined set comprises and to the corresponding transmission LRAG the determined set of reachability information for each partition cover covering the partition, wherein the LRAG is configured reachability information based on the set of instances of the at least one virtual endpoint.
  9. 9. 根据权利要求4所述的方法,其中: 接收所述可达性信息中的更新; 确定由所述可达性信息中的所述更新影响的一个或多个覆盖分区,受影响的所述覆盖分区具有附接到与所述可达性信息中的所述更新相关的所述虚拟网络中的一个虚拟网络的至少一个虚拟端点;以及向所确定的所述一个或多个覆盖分区传输所述可达性信息中的所述更新。 9. The method as claimed in claim 4, wherein: receiving the updated reachability information; a is determined by the effect of the updated reachability information or a plurality of partitions cover, the affected said cover having a partition attached to at least one virtual terminal associated with the virtual network is a virtual network with the updated reachability information; and one or more partitions covering the determined transmission to the the reachability information update.
  10. 10. 根据权利要求4所述的方法,其中: 所述覆盖分区中的每个覆盖分区包括本地可达性接入网关(“LRAG”);以及传输所确定的所述可达性信息集合包括向与所述覆盖分区中的每个覆盖分区相对应的所述LRAG传输所确定的所述可达性信息集合,其中所述LRAG被配置为基于所述可达性信息集合来建立至少一个虚拟端点;以及所述方法还包括: 接收关于由所述LRAG对所述虚拟端点的建立的状态通知; 基于所述虚拟端点的所述建立来确定哪个其他覆盖分区受影响,受影响的所述覆盖分区具有附接到包含所建立的所述虚拟端点的所述虚拟网络的至少一个虚拟端点;以及关于所述虚拟端点的所述建立向所确定的受影响的所述覆盖分区进行通知。 10. The method according to claim 4, wherein: each of said partition covering the partition cover includes a local reachability access gateway ( "LRAG"); and said transmitting reachability information of the determined set comprises and the cover to set the reachability information transmission LRAG cover each partition corresponding to partition the determined, wherein the LRAG is configured based on the set of reachability information establishing at least one virtual inclusive; and the method further comprises: receiving notification about the status of the endpoint to the virtual LRAG established; to determine which other affected partition cover, said cover of said affected virtual endpoint based on the establishment of virtual partition having at least one end attached to the established virtual comprising the virtual network endpoint; and virtual endpoints with respect to the establishment of the partition to the affected covering the determined notification.
CN 201580057692 2014-10-26 2015-10-23 Method for reachability management in computer networks CN107078937A (en)

Priority Applications (4)

Application Number Priority Date Filing Date Title
US201462068709 true 2014-10-26 2014-10-26
US62/068,709 2014-10-26
US14555865 US9923800B2 (en) 2014-10-26 2014-11-28 Method for reachability management in computer networks
PCT/US2015/057030 WO2016069381A1 (en) 2014-10-26 2015-10-23 Method for reachability management in computer networks

Publications (1)

Publication Number Publication Date
CN107078937A true true CN107078937A (en) 2017-08-18

Family

ID=55792879

Family Applications (1)

Application Number Title Priority Date Filing Date
CN 201580057692 CN107078937A (en) 2014-10-26 2015-10-23 Method for reachability management in computer networks

Country Status (4)

Country Link
US (1) US9923800B2 (en)
EP (1) EP3210111A1 (en)
CN (1) CN107078937A (en)
WO (1) WO2016069381A1 (en)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20170118005A1 (en) * 2015-10-23 2017-04-27 International Business Machines Corporation Non-disruptively splitting a coordinated timing network
WO2017205099A1 (en) * 2016-05-24 2017-11-30 Level 3 Communications, Llc Route selection system for a communication network and method of operating the same

Family Cites Families (61)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5493716A (en) * 1994-04-14 1996-02-20 Motorola, Inc. Method of operating a radio
US7095740B1 (en) 1998-06-30 2006-08-22 Nortel Networks Limited Method and apparatus for virtual overlay networks
US7272643B1 (en) * 2000-09-13 2007-09-18 Fortinet, Inc. System and method for managing and provisioning virtual routers
US7346279B1 (en) * 2002-03-25 2008-03-18 Forster Energy Llc Optical transceiver using heterodyne detection and a transmitted reference clock
US7580399B2 (en) * 2005-09-14 2009-08-25 Cisco Technology, Inc. Automatic partitioning of wireless access points into overlay and underlay networks
US7738401B2 (en) 2005-10-20 2010-06-15 At&T Intellectual Property I, L.P. System and method for overlaying a hierarchical network design on a full mesh network
US7761573B2 (en) 2005-12-07 2010-07-20 Avaya Inc. Seamless live migration of virtual machines across optical networks
US8233489B2 (en) 2006-11-27 2012-07-31 Telefonaktiebolaget Lm Ericsson (Publ) System, method, and router for routing data packets in an overlay network
EP1962192A1 (en) 2007-02-21 2008-08-27 Deutsche Telekom AG Method and system for the transparent migration of virtual machine storage
US8166205B2 (en) 2007-07-31 2012-04-24 Cisco Technology, Inc. Overlay transport virtualization
US7996510B2 (en) 2007-09-28 2011-08-09 Intel Corporation Virtual clustering for scalable network control and management
WO2009115132A1 (en) 2008-03-20 2009-09-24 Telefonaktiebolaget Lm Ericsson (Publ) Method and apparatus for use in a communications network
US8429647B2 (en) 2009-05-06 2013-04-23 Vmware, Inc. Virtual machine migration across network by publishing routes to the associated virtual networks via virtual router after the start of migration of the virtual machine
US9210065B2 (en) 2009-06-22 2015-12-08 Alcatel Lucent Providing cloud-based services using dynamic network virtualization
US8837521B2 (en) 2009-11-12 2014-09-16 Eci Telecom Ltd. Ethernet network within MPLS network
US8705513B2 (en) 2009-12-15 2014-04-22 At&T Intellectual Property I, L.P. Methods and apparatus to communicatively couple virtual private networks to virtual machines within distributive computing networks
US8966027B1 (en) * 2010-05-24 2015-02-24 Amazon Technologies, Inc. Managing replication of computing nodes for provided computer networks
US8473557B2 (en) 2010-08-24 2013-06-25 At&T Intellectual Property I, L.P. Methods and apparatus to migrate virtual machines between distributive computing networks across a wide area network
JP5817915B2 (en) * 2011-04-13 2015-11-18 富士通株式会社 A receiver and a receiving method
CN102821028B (en) 2011-06-08 2016-03-30 上海贝尔股份有限公司 Virtual machine migration support in a multi-protocol label and a corresponding network equipment
US8804745B1 (en) 2011-06-27 2014-08-12 Amazon Technologies, Inc. Virtualization mapping
US9424144B2 (en) 2011-07-27 2016-08-23 Microsoft Technology Licensing, Llc Virtual machine migration to minimize packet loss in virtualized network
WO2013020126A1 (en) * 2011-08-04 2013-02-07 Midokura Pte. Ltd. System and method for implementing and managing virtual networks
US20130034094A1 (en) 2011-08-05 2013-02-07 International Business Machines Corporation Virtual Switch Data Control In A Distributed Overlay Network
US9274825B2 (en) 2011-08-16 2016-03-01 Microsoft Technology Licensing, Llc Virtualization gateway between virtualized and non-virtualized networks
US9167501B2 (en) 2011-08-29 2015-10-20 Telefonaktiebolaget L M Ericsson (Publ) Implementing a 3G packet core in a cloud computer with openflow data and control planes
US20130086298A1 (en) 2011-10-04 2013-04-04 International Business Machines Corporation Live Logical Partition Migration with Stateful Offload Connections Using Context Extraction and Insertion
US9577762B2 (en) * 2011-11-21 2017-02-21 Ciena Corporation Subcarrier power balance control
US8730980B2 (en) 2011-12-27 2014-05-20 Cisco Technology, Inc. Architecture for scalable virtual network services
US9071458B2 (en) * 2012-01-30 2015-06-30 Cisco Technology, Inc. Dual adjacency between edge devices at a network site
US9426068B2 (en) * 2012-02-24 2016-08-23 Futurewei Technologies, Inc. Balancing of forwarding and address resolution in overlay networks
EP2817926A1 (en) * 2012-02-24 2014-12-31 Huawei Technologies Co., Ltd. Delegate forwarding and address resolution in fragmented network
US9184981B2 (en) 2012-03-09 2015-11-10 Futurewei Technologies, Inc. System and apparatus for distributed mobility management based network layer virtual machine mobility protocol
JP5906896B2 (en) 2012-03-29 2016-04-20 富士通株式会社 Network system and communication control method
US9064216B2 (en) 2012-06-06 2015-06-23 Juniper Networks, Inc. Identifying likely faulty components in a distributed system
US20140006585A1 (en) * 2012-06-29 2014-01-02 Futurewei Technologies, Inc. Providing Mobility in Overlay Networks
WO2014030229A1 (en) 2012-08-22 2014-02-27 株式会社日立製作所 Virtual computer system for restoring network connection of virtual computer for which live migration has been performed
JP5835846B2 (en) 2012-08-29 2015-12-24 株式会社日立製作所 Migration method of network system and a virtual node
US8837476B2 (en) 2012-09-07 2014-09-16 International Business Machines Corporation Overlay network capable of supporting storage area network (SAN) traffic
US20140086253A1 (en) * 2012-09-26 2014-03-27 Futurewei Technologies, Inc. Overlay Virtual Gateway for Overlay Networks
US9727386B2 (en) * 2012-10-12 2017-08-08 Futurewei Technologies, Inc. Method and apparatus for network resource virtual partitioning
US9240944B2 (en) 2012-10-19 2016-01-19 Cisco Technology, Inc. Overlay services in communication networks
US9143442B2 (en) 2012-12-12 2015-09-22 Cisco Technology, Inc. Flexible and scalable virtual network segment pruning
US9116727B2 (en) 2013-01-15 2015-08-25 Lenovo Enterprise Solutions (Singapore) Pte. Ltd. Scalable network overlay virtualization using conventional virtual switches
US9477506B2 (en) 2013-02-12 2016-10-25 Futurewei Technologies, Inc. Dynamic virtual machines migration over information centric networks
CN103997414B (en) * 2013-02-18 2016-11-09 华为技术有限公司 Generating method and a network configuration information control unit
US9525564B2 (en) * 2013-02-26 2016-12-20 Zentera Systems, Inc. Secure virtual network platform for enterprise hybrid cloud computing environments
US9374241B2 (en) 2013-03-14 2016-06-21 International Business Machines Corporation Tagging virtual overlay packets in a virtual networking system
US9794379B2 (en) * 2013-04-26 2017-10-17 Cisco Technology, Inc. High-efficiency service chaining with agentless service nodes
US9329894B2 (en) 2013-08-13 2016-05-03 Vmware, Inc. Method and apparatus for extending local area networks between clouds and permanently migrating virtual machines using static network addresses
WO2015040866A1 (en) 2013-09-19 2015-03-26 日本電気株式会社 Communication device and method for controlling communication in communication system
US9628290B2 (en) 2013-10-09 2017-04-18 International Business Machines Corporation Traffic migration acceleration for overlay virtual environments
US9124536B2 (en) 2013-12-12 2015-09-01 International Business Machines Corporation Managing data flows in overlay networks
US20150281099A1 (en) 2014-03-28 2015-10-01 International Business Machines Corporation QUALITY OF SERVICE (QoS) FOR MULTI-TENANT-AWARE OVERLAY VIRTUAL NETWORKS
US10063473B2 (en) * 2014-04-30 2018-08-28 Brocade Communications Systems LLC Method and system for facilitating switch virtualization in a network of interconnected switches
WO2015175434A1 (en) * 2014-05-12 2015-11-19 Netapp, Inc. Bridging clouds
US9313117B2 (en) 2014-05-27 2016-04-12 Telefonaktiebolaget L M Ericsson (Publ) Alternate method to give operators flexibility to choose LFAs
US9509599B2 (en) 2014-08-04 2016-11-29 Telefonaktiebolaget L M Ericsson (Publ) Self-bootstrapping BFD session over MPLS LSP
US9900263B2 (en) 2014-09-29 2018-02-20 Alcatel-Lucent Usa Inc. Non-overlay resource access in datacenters using overlay networks
US20160105408A1 (en) * 2014-10-10 2016-04-14 Adp, Llc Securing application programming interfaces (apis) through infrastructure virtualization
US20160191341A1 (en) * 2014-12-29 2016-06-30 Verizon Patent And Licensing Inc. Secure cloud interconnect private routing

Also Published As

Publication number Publication date Type
US9923800B2 (en) 2018-03-20 grant
WO2016069381A1 (en) 2016-05-06 application
US20160119219A1 (en) 2016-04-28 application
EP3210111A1 (en) 2017-08-30 application

Similar Documents

Publication Publication Date Title
Nascimento et al. Virtual routers as a service: the routeflow approach leveraging software-defined networks
US8239572B1 (en) Custom routing decisions
US8296459B1 (en) Custom routing decisions
US20100169467A1 (en) Method and apparatus for determining a network topology during network provisioning
US8396946B1 (en) Managing integration of external nodes into provided computer networks
US8194680B1 (en) Managing communications for modified computer networks
US20130058351A1 (en) Use of tunnels to hide network addresses
US20130003735A1 (en) Dynamically provisioning middleboxes
US8705513B2 (en) Methods and apparatus to communicatively couple virtual private networks to virtual machines within distributive computing networks
US20100257263A1 (en) Method and apparatus for implementing and managing virtual switches
US20090327392A1 (en) Method and system for creating a virtual router in a blade chassis to maintain connectivity
US20140201374A1 (en) Network Function Virtualization for a Network Device
US20100246443A1 (en) Providing logical networking functionality for managed computer networks
US8224931B1 (en) Managing use of intermediate destination computing nodes for provided computer networks
US8683023B1 (en) Managing communications involving external nodes of provided computer networks
US8296434B1 (en) Providing dynamically scaling computing load balancing
US7991859B1 (en) Using virtual networking devices to connect managed computer networks
US7953865B1 (en) Using virtual networking devices to manage routing communications between connected computer networks
US8484353B1 (en) Resource placement templates for virtual networks
US8958298B2 (en) Centralized logical L3 routing
US20140068703A1 (en) System and method providing policy based data center network automation
US8224971B1 (en) Using virtual networking devices and routing information to initiate external actions
US8644188B1 (en) Providing virtual networking functionality for managed computer networks
US20130329548A1 (en) Re-routing network traffic after link failure
US7937438B1 (en) Using virtual networking devices to manage external connections

Legal Events

Date Code Title Description
PB01
SE01